BrightLocal MCP Server and API by Cotlet is an MCP server published by dev.cotlet, hosted at cotlet.dev. When last checked on 2026-11-21 it was working: it answers and lists its tools. It declares 47 tools, including cotlet_whoami, cotlet_apps, cotlet_request_apps, cotlet_get_call, cotlet_upload_file.
BrightLocal local SEO management MCP server: list locations, get rank tracker report.
1,987 connections through 4 shared values. Tap any node.
Squares are this server's values; dots are other servers sharing them. A shared address or publisher is a lead, not proof of a common operator.
Inferred from the host name and headers: what a server runs on, not who runs it.
The Cotlet account this connection acts as: email, workspace, access status, the API key or OAuth client in use with its scope, the apps the workspace may call, its credit balance, and the app the user signed up for with its first task and sign-in link. Free. Needs the user's Cotlet API key or sign-in.
No parameters.
{
"name": "cotlet_whoami",
"title": "Cotlet: who am I",
"description": "The Cotlet account this connection acts as: email, workspace, access status, the API key or OAuth client in use with its scope, the apps the workspace may call, its credit balance, and the app the user signed up for with its first task and sign-in link. Free. Needs the user's Cotlet API key or sign-in.",
"inputSchema": {
"type": "object",
"properties": {},
"additionalProperties": false
},
"annotations": {
"title": "Cotlet: who am I",
"readOnlyHint": true,
"openWorldHint": false,
"destructiveHint": false
}
}The apps of the user's workspace and whether each works now: the app account in the user's Cloud Browser (connected, signed out, signed in but not connected), and the one step the user has to take, with the console link. Free. Needs the user's Cotlet API key or sign-in.
| Parameter | Type | Description |
|---|---|---|
| app | string | Only this app, e.g. skool. |
{
"name": "cotlet_apps",
"title": "Cotlet: apps I can use",
"description": "The apps of the user's workspace and whether each works now: the app account in the user's Cloud Browser (connected, signed out, signed in but not connected), and the one step the user has to take, with the console link. Free. Needs the user's Cotlet API key or sign-in.",
"inputSchema": {
"type": "object",
"properties": {
"app": {
"type": "string",
"description": "Only this app, e.g. skool."
}
},
"additionalProperties": false
},
"annotations": {
"title": "Cotlet: apps I can use",
"readOnlyHint": true,
"openWorldHint": false,
"destructiveHint": false
}
}Requests access to apps for the user's workspace, as Request access in the console: every app is granted at once. Not needed to work in an app: the user's AI works in any web app in their Web browser with cotlet_app_guide. An app with dedicated tools gets them after the user signs in to it in their Cloud Browser. Access says nothing about whether a task works there: check that in the browser. Takes app slugs as listed at https://cotlet.dev/api/v1/apps. Free. Needs the user's Cotlet API key or sign-in.
| Parameter | Type | Description |
|---|---|---|
| apps * | array | App slugs, e.g. ["skool", "substack"]. |
| use_case | string | What the user wants the agent to do in these apps, in their words. |
{
"name": "cotlet_request_apps",
"title": "Cotlet: request access to apps",
"description": "Requests access to apps for the user's workspace, as Request access in the console: every app is granted at once. Not needed to work in an app: the user's AI works in any web app in their Web browser with cotlet_app_guide. An app with dedicated tools gets them after the user signs in to it in their Cloud Browser. Access says nothing about whether a task works there: check that in the browser. Takes app slugs as listed at https://cotlet.dev/api/v1/apps. Free. Needs the user's Cotlet API key or sign-in.",
"inputSchema": {
"type": "object",
"required": [
"apps"
],
"properties": {
"apps": {
"type": "array",
"items": {
"type": "string"
},
"maxItems": 10,
"minItems": 1,
"description": "App slugs, e.g. [\"skool\", \"substack\"]."
},
"use_case": {
"type": "string",
"maxLength": 1000,
"description": "What the user wants the agent to do in these apps, in their words."
}
},
"additionalProperties": false
},
"annotations": {
"title": "Cotlet: request access to apps",
"readOnlyHint": false,
"openWorldHint": false,
"destructiveHint": false
}
}Status of an earlier Cotlet call, by its call_id: pending (waits for the owner's approval in the Cotlet console), approved, running, success, rejected, expired, blocked or failed. For a call that answered with status pending or running.
| Parameter | Type | Description |
|---|---|---|
| call_id * | string | call_id from the earlier call |
{
"name": "cotlet_get_call",
"title": "Cotlet: check a call",
"description": "Status of an earlier Cotlet call, by its call_id: pending (waits for the owner's approval in the Cotlet console), approved, running, success, rejected, expired, blocked or failed. For a call that answered with status pending or running.",
"inputSchema": {
"type": "object",
"required": [
"call_id"
],
"properties": {
"call_id": {
"type": "string",
"description": "call_id from the earlier call"
}
},
"additionalProperties": false
},
"annotations": {
"title": "Cotlet: check a call",
"readOnlyHint": true,
"openWorldHint": false,
"destructiveHint": false
}
}Returns a one-time upload_url and a file_id for a local file (an image for a post, an attachment). The file is sent to upload_url with an HTTP PUT; an argument that takes a file accepts {"file_id": "..."}. Up to 25 MB, the URL takes one stored file (a failed PUT can be sent again). Free. Needs the user's Cotlet API key or sign-in.
| Parameter | Type | Description |
|---|---|---|
| name | string | File name, e.g. photo.jpg. |
| content_type | string | MIME type, e.g. image/jpeg. |
{
"name": "cotlet_upload_file",
"title": "Cotlet: upload a file for a tool",
"description": "Returns a one-time upload_url and a file_id for a local file (an image for a post, an attachment). The file is sent to upload_url with an HTTP PUT; an argument that takes a file accepts {\"file_id\": \"...\"}. Up to 25 MB, the URL takes one stored file (a failed PUT can be sent again). Free. Needs the user's Cotlet API key or sign-in.",
"inputSchema": {
"type": "object",
"properties": {
"name": {
"type": "string",
"description": "File name, e.g. photo.jpg."
},
"content_type": {
"type": "string",
"description": "MIME type, e.g. image/jpeg."
}
},
"additionalProperties": false
},
"annotations": {
"title": "Cotlet: upload a file for a tool",
"readOnlyHint": false,
"openWorldHint": false,
"destructiveHint": false
}
}Sends a report to the Cotlet team: a tool that failed or returned wrong data, an error you could not get past, or a step the browser could not do, with the page, the step and what you saw. A missing dedicated tool is not a problem to report: do the task in the browser. A feature the user asks for goes as feature_request. A report promises nothing: tell the user it was sent, never that something will be built or fixed, or when. The report carries the error text and call_id when there is one, never passwords or tokens. Needs the user's Cotlet API key or sign-in.
| Parameter | Type | Description |
|---|---|---|
| app | any | App slug the report is about, e.g. 'skool', or for a site in the web browser its host, e.g. 'app.example.com'. |
| kind * | string | bug: a tool did the wrong thing or returned wrong data. error: a call failed or returned an error you could not get past. feature_request: something new the user asked for. missing_feature: a step the task needed that you tried and could not do, in the browser or with a tool. other: anything else. |
| tool | any | Tool or endpoint name, e.g. 'skool_list_members'. |
| title * | string | One line, e.g. 'skool_list_members stops after 50 members'. |
| client | any | Agent or tool sending this, e.g. 'Claude Code'. |
| call_id | any | call_id of the call that went wrong, if any. |
| description * | string | What the user asked for, what you tried, what you expected and what happened, with the error text if there was one. No passwords, tokens or other secrets. |
Starts the user's BrightLocal Cloud Browser (a real Chrome on Cotlet, signed in to BrightLocal as the user; use it for what the BrightLocal tools do not cover) and opens `url`. Call it first. Only BrightLocal pages open. Answers the page after it: the elements and text in view, with the same numbers. In BrightLocal it serves these actions: List locations, Get rank tracker report, Get local search grid report, List reviews, Update rank tracker keywords, Re-run report.
| Parameter | Type | Description |
|---|---|---|
| url | string | A public http or https address, e.g. https://example.com. |
{
"name": "cotlet_browser_open",
"title": "Open the browser",
"description": "Starts the user's BrightLocal Cloud Browser (a real Chrome on Cotlet, signed in to BrightLocal as the user; use it for what the BrightLocal tools do not cover) and opens `url`. Call it first. Only BrightLocal pages open. Answers the page after it: the elements and text in view, with the same numbers. In BrightLocal it serves these actions: List locations, Get rank tracker report, Get local search grid report, List reviews, Update rank tracker keywords, Re-run report.",
"inputSchema": {
"type": "object",
"properties": {
"url": {
"type": "string",
"format": "uri",
"description": "A public http or https address, e.g. https://example.com."
}
},
"additionalProperties": false
},
"annotations": {
"title": "Open the browser",
"readOnlyHint": true,
"openWorldHint": true,
"idempotentHint": false,
"destructiveHint": false
}
}Opens `url` in the current tab, or goes `history` back or forward. Answers the page after it: the elements and text in view, with the same numbers.
| Parameter | Type | Description |
|---|---|---|
| tab | string | The Tab id of the last answer. The step acts only while that tab is the shown one; if the user or another client showed another tab, it does nothing and answers tab_changed. Leave it out to act on the shown tab. |
| url | string | A public http or https address, e.g. https://example.com. |
| dialog | string | How to answer a native dialog (confirm, prompt, 'leave this page?') this step opens: accept presses OK, dismiss presses Cancel. Default: OK for an alert, Cancel for every other dialog. |
| history | string | Instead of `url`. |
| dialog_text | string | Text for a prompt dialog this step opens; implies accept. |
{
"name": "cotlet_browser_navigate",
"title": "Go to a page",
"description": "Opens `url` in the current tab, or goes `history` back or forward. Answers the page after it: the elements and text in view, with the same numbers.",
"inputSchema": {
"type": "object",
"properties": {
"tab": {
"type": "string",
"maxLength": 64,
"minLength": 1,
"description": "The Tab id of the last answer. The step acts only while that tab is the shown one; if the user or another client showed another tab, it does nothing and answers tab_changed. Leave it out to act on the shown tab."
},
"url": {
"type": "string",
"format": "uri",
"description": "A public http or https address, e.g. https://example.com."
},
"dialog": {
"enum": [
"accept",
"dismiss"
],
"type": "string",
"description": "How to answer a native dialog (confirm, prompt, 'leave this page?') this step opens: accept presses OK, dismiss presses Cancel. Default: OK for an alert, Cancel for every other dialog."
},
"history": {
"enum": [
"back",
"forward"
],
"type": "string",
"description": "Instead of `url`."
},
"dialog_text": {
"type": "string",
"maxLength": 1000,
"description": "Text for a prompt dialog this step opens; implies accept."
}
},
"additionalProperties": false
},
"annotations": {
"title": "Go to a page",
"readOnlyHint": true,
"openWorldHint": true,
"idempotentHint": false,
"destructiveHint": false
}
}The whole current page: its text (up to 20,000 characters) and a numbered list of its links, buttons, fields and other controls, open dialogs first. Use it on a new page or when a step's answer is not enough; `element` reads only inside one element (a dialog, a form, a list). Never returns field values, cookies or storage.
| Parameter | Type | Description |
|---|---|---|
| tab | string | The Tab id of the last answer. The step acts only while that tab is the shown one; if the user or another client showed another tab, it does nothing and answers tab_changed. Leave it out to act on the shown tab. |
| element | integer | Read only inside this element. |
{
"name": "cotlet_browser_read",
"title": "Read the page",
"description": "The whole current page: its text (up to 20,000 characters) and a numbered list of its links, buttons, fields and other controls, open dialogs first. Use it on a new page or when a step's answer is not enough; `element` reads only inside one element (a dialog, a form, a list). Never returns field values, cookies or storage.",
"inputSchema": {
"type": "object",
"properties": {
"tab": {
"type": "string",
"maxLength": 64,
"minLength": 1,
"description": "The Tab id of the last answer. The step acts only while that tab is the shown one; if the user or another client showed another tab, it does nothing and answers tab_changed. Leave it out to act on the shown tab."
},
"element": {
"type": "integer",
"minimum": 1,
"description": "Read only inside this element."
}
},
"additionalProperties": false
},
"annotations": {
"title": "Read the page",
"readOnlyHint": true,
"openWorldHint": true,
"idempotentHint": true,
"destructiveHint": false
}
}Finds `text` on the whole current page, frames included: the elements whose label holds it, with their numbers, and each line of text that holds it. Use it instead of reading or scrolling a long page for one thing.
| Parameter | Type | Description |
|---|---|---|
| tab | string | The Tab id of the last answer. The step acts only while that tab is the shown one; if the user or another client showed another tab, it does nothing and answers tab_changed. Leave it out to act on the shown tab. |
| kind | string | Only elements of this kind. Default: any. |
| text * | string | Words to look for, any case. |
{
"name": "cotlet_browser_find",
"title": "Find on the page",
"description": "Finds `text` on the whole current page, frames included: the elements whose label holds it, with their numbers, and each line of text that holds it. Use it instead of reading or scrolling a long page for one thing.",
"inputSchema": {
"type": "object",
"required": [
"text"
],
"properties": {
"tab": {
"type": "string",
"maxLength": 64,
"minLength": 1,
"description": "The Tab id of the last answer. The step acts only while that tab is the shown one; if the user or another client showed another tab, it does nothing and answers tab_changed. Leave it out to act on the shown tab."
},
"kind": {
"enum": [
"link",
"button",
"field",
"any"
],
"type": "string",
"description": "Only elements of this kind. Default: any."
},
"text": {
"type": "string",
"maxLength": 200,
"description": "Words to look for, any case."
}
},
"additionalProperties": false
},
"annotations": {
"title": "Find on the page",
"readOnlyHint": true,
"openWorldHint": true,
"idempotentHint": true,
"destructiveHint": false
}
}A JPEG of the visible part of the page. Use it for boards, canvases, maps, charts and layout that the text does not show, then click or drag by `x`, `y` of the image.
| Parameter | Type | Description |
|---|---|---|
| tab | string | The Tab id of the last answer. The step acts only while that tab is the shown one; if the user or another client showed another tab, it does nothing and answers tab_changed. Leave it out to act on the shown tab. |
{
"name": "cotlet_browser_screenshot",
"title": "See the page",
"description": "A JPEG of the visible part of the page. Use it for boards, canvases, maps, charts and layout that the text does not show, then click or drag by `x`, `y` of the image.",
"inputSchema": {
"type": "object",
"properties": {
"tab": {
"type": "string",
"maxLength": 64,
"minLength": 1,
"description": "The Tab id of the last answer. The step acts only while that tab is the shown one; if the user or another client showed another tab, it does nothing and answers tab_changed. Leave it out to act on the shown tab."
}
},
"additionalProperties": false
},
"annotations": {
"title": "See the page",
"readOnlyHint": true,
"openWorldHint": true,
"idempotentHint": true,
"destructiveHint": false
}
}Scrolls with the mouse wheel: `down` or `up` by `screens`, to `top` or `bottom`, until `element` is in view, or inside a panel or list (`inside`). Content that loads on scroll appears. Answers the page after it: the elements and text in view, with the same numbers.
| Parameter | Type | Description |
|---|---|---|
| tab | string | The Tab id of the last answer. The step acts only while that tab is the shown one; if the user or another client showed another tab, it does nothing and answers tab_changed. Leave it out to act on the shown tab. |
| inside | integer | Scroll inside this element, not the page. |
| element | integer | Scroll until this element is in view. |
| screens | number | Viewport heights, for down and up. Default: 0.8. |
| direction | string | Default: down. |
{
"name": "cotlet_browser_scroll",
"title": "Scroll the page",
"description": "Scrolls with the mouse wheel: `down` or `up` by `screens`, to `top` or `bottom`, until `element` is in view, or inside a panel or list (`inside`). Content that loads on scroll appears. Answers the page after it: the elements and text in view, with the same numbers.",
"inputSchema": {
"type": "object",
"properties": {
"tab": {
"type": "string",
"maxLength": 64,
"minLength": 1,
"description": "The Tab id of the last answer. The step acts only while that tab is the shown one; if the user or another client showed another tab, it does nothing and answers tab_changed. Leave it out to act on the shown tab."
},
"inside": {
"type": "integer",
"minimum": 1,
"description": "Scroll inside this element, not the page."
},
"element": {
"type": "integer",
"minimum": 1,
"description": "Scroll until this element is in view."
},
"screens": {
"type": "number",
"maximum": 10,
"description": "Viewport heights, for down and up. Default: 0.8.",
"exclusiveMinimum": 0
},
"direction": {
"enum": [
"down",
"up",
"top",
"bottom"
],
"type": "string",
"description": "Default: down."
}
},
"additionalProperties": false
},
"annotations": {
"title": "Scroll the page",
"readOnlyHint": true,
"openWorldHint": true,
"idempotentHint": true,
"destructiveHint": false
}
}Clicks element `element`, or point `x`, `y` of the screenshot; `double` double-clicks, `button: right` right-clicks. Answers the page after it: the elements and text in view, with the same numbers. Says when nothing changed. A link that would open a new tab opens in this one. Buttons that pay or buy, and sign-in and account pages, are refused.
| Parameter | Type | Description |
|---|---|---|
| x | number | Instead of `element`: pixels from the left of the screenshot. |
| y | number | With `x`: pixels from the top of the screenshot. |
| tab | string | The Tab id of the last answer. The step acts only while that tab is the shown one; if the user or another client showed another tab, it does nothing and answers tab_changed. Leave it out to act on the shown tab. |
| button | string | right opens the page's own context menu. Default: left. |
| dialog | string | How to answer a native dialog (confirm, prompt, 'leave this page?') this step opens: accept presses OK, dismiss presses Cancel. Default: OK for an alert, Cancel for every other dialog. |
| double | boolean | Double-click. |
| element | integer | The element's number from the last read or step answer. |
| dialog_text | string | Text for a prompt dialog this step opens; implies accept. |
Rests the pointer on an element or a point, to open a hover menu, a tooltip or a preview. Answers the page after it: the elements and text in view, with the same numbers.
| Parameter | Type | Description |
|---|---|---|
| x | number | Instead of `element`: pixels from the left of the screenshot. |
| y | number | With `x`: pixels from the top of the screenshot. |
| tab | string | The Tab id of the last answer. The step acts only while that tab is the shown one; if the user or another client showed another tab, it does nothing and answers tab_changed. Leave it out to act on the shown tab. |
| element | integer | The element's number from the last read or step answer. |
{
"name": "cotlet_browser_hover",
"title": "Point at the page",
"description": "Rests the pointer on an element or a point, to open a hover menu, a tooltip or a preview. Answers the page after it: the elements and text in view, with the same numbers.",
"inputSchema": {
"type": "object",
"properties": {
"x": {
"type": "number",
"minimum": 0,
"description": "Instead of `element`: pixels from the left of the screenshot."
},
"y": {
"type": "number",
"minimum": 0,
"description": "With `x`: pixels from the top of the screenshot."
},
"tab": {
"type": "string",
"maxLength": 64,
"minLength": 1,
"description": "The Tab id of the last answer. The step acts only while that tab is the shown one; if the user or another client showed another tab, it does nothing and answers tab_changed. Leave it out to act on the shown tab."
},
"element": {
"type": "integer",
"minimum": 1,
"description": "The element's number from the last read or step answer."
}
},
"additionalProperties": false
},
"annotations": {
"title": "Point at the page",
"readOnlyHint": true,
"openWorldHint": true,
"idempotentHint": true,
"destructiveHint": false
}
}Drags from one element or point to another: a card between columns, a piece on a board, a slider's handle. Answers the page after it: the elements and text in view, with the same numbers.
| Parameter | Type | Description |
|---|---|---|
| to * | object | An element number, or x and y of the screenshot. |
| tab | string | The Tab id of the last answer. The step acts only while that tab is the shown one; if the user or another client showed another tab, it does nothing and answers tab_changed. Leave it out to act on the shown tab. |
| from * | object | An element number, or x and y of the screenshot. |
| dialog | string | How to answer a native dialog (confirm, prompt, 'leave this page?') this step opens: accept presses OK, dismiss presses Cancel. Default: OK for an alert, Cancel for every other dialog. |
| dialog_text | string | Text for a prompt dialog this step opens; implies accept. |
{
"name": "cotlet_browser_drag",
"title": "Drag on the page",
"description": "Drags from one element or point to another: a card between columns, a piece on a board, a slider's handle. Answers the page after it: the elements and text in view, with the same numbers.",
"inputSchema": {
"type": "object",
"required": [
"from",
"to"
],
"properties": {
"to": {
"type": "object",
"properties": {
"x": {
"type": "number",
"minimum": 0,
"description": "Instead of `element`: pixels from the left of the screenshot."
},
"y": {
"type": "number",
"minimum": 0,
"description": "With `x`: pixels from the top of the screenshot."
},
"element": {
"type": "integer",
"minimum": 1,
"description": "The element's number from the last read or step answer."
}
},
"description": "An element number, or x and y of the screenshot.",
"additionalProperties": false
},
"tab": {
"type": "string",
"maxLength": 64,
"minLength": 1,
"description": "The Tab id of the last answer. The step acts only while that tab is the shown one; if the user or another client showed another tab, it does nothing and answers tab_changed. Leave it out to act on the shown tab."
},
"from": {
"type": "object",
"properties": {
"x": {
"type": "number",
"minimum": 0,
"description": "Instead of `element`: pixels from the left of the screenshot."
},
"y": {
"type": "number",
"minimum": 0,
"description": "With `x`: pixels from the top of the screenshot."
},
"element": {
"type": "integer",
"minimum": 1,
"description": "The element's number from the last read or step answer."
}
},
"description": "An element number, or x and y of the screenshot.",
"additionalProperties": false
},
"dialog": {
"enum": [
"accept",
"dismiss"
],
"type": "string",
"description": "How to answer a native dialog (confirm, prompt, 'leave this page?') this step opens: accept presses OK, dismiss presses Cancel. Default: OK for an alert, Cancel for every other dialog."
},
"dialog_text": {
"type": "string",
"maxLength": 1000,
"description": "Text for a prompt dialog this step opens; implies accept."
}
},
"additionalProperties": false
},
"annotations": {
"title": "Drag on the page",
"readOnlyHint": false,
"openWorldHint": true,
"idempotentHint": false,
"destructiveHint": true
}
}Types `text` into field `element`, replacing what it held; `submit` presses Enter after it. For several fields use fill_form. Without `element` the text goes where the focus is, as a person types after clicking: for spreadsheet cells and editors that read does not number (Google Sheets, Docs), click the place first; there a tab in `text` presses Tab and a line break Enter, so one call fills a table. Answers the page after it: the elements and text in view, with the same numbers. A password or code the user gave you goes in like any text; card fields are refused.
| Parameter | Type | Description |
|---|---|---|
| tab | string | The Tab id of the last answer. The step acts only while that tab is the shown one; if the user or another client showed another tab, it does nothing and answers tab_changed. Leave it out to act on the shown tab. |
| text * | string | The text to type. |
| dialog | string | How to answer a native dialog (confirm, prompt, 'leave this page?') this step opens: accept presses OK, dismiss presses Cancel. Default: OK for an alert, Cancel for every other dialog. |
| slowly | boolean | Key by key, for a search or address field whose suggestions do not appear. |
| submit | boolean | Press Enter after typing, e.g. to search. |
| element | integer | The field's number from the last read. Leave it out to type where the focus is. |
| dialog_text | string |
Fills several fields in one step: text fields take text, drop-downs an option's label, checkboxes, radios and switches true or false. Stops at the first field that fails and names those filled. Does not send the form: click its button after. Answers the page after it: the elements and text in view, with the same numbers.
| Parameter | Type | Description |
|---|---|---|
| tab | string | The Tab id of the last answer. The step acts only while that tab is the shown one; if the user or another client showed another tab, it does nothing and answers tab_changed. Leave it out to act on the shown tab. |
| dialog | string | How to answer a native dialog (confirm, prompt, 'leave this page?') this step opens: accept presses OK, dismiss presses Cancel. Default: OK for an alert, Cancel for every other dialog. |
| fields * | array | The fields in the order a person fills them. |
| dialog_text | string | Text for a prompt dialog this step opens; implies accept. |
{
"name": "cotlet_browser_fill_form",
"title": "Fill in a form",
"description": "Fills several fields in one step: text fields take text, drop-downs an option's label, checkboxes, radios and switches true or false. Stops at the first field that fails and names those filled. Does not send the form: click its button after. Answers the page after it: the elements and text in view, with the same numbers.",
"inputSchema": {
"type": "object",
"required": [
"fields"
],
"properties": {
"tab": {
"type": "string",
"maxLength": 64,
"minLength": 1,
"description": "The Tab id of the last answer. The step acts only while that tab is the shown one; if the user or another client showed another tab, it does nothing and answers tab_changed. Leave it out to act on the shown tab."
},
"dialog": {
"enum": [
"accept",
"dismiss"
],
"type": "string",
"description": "How to answer a native dialog (confirm, prompt, 'leave this page?') this step opens: accept presses OK, dismiss presses Cancel. Default: OK for an alert, Cancel for every other dialog."
},
"fields": {
"type": "array",
"items": {
"type": "object",
"required": [
"element",
"value"
],
"properties": {
"value": {
"type": [
"string",
"boolean"
],
"description": "Text, option, or true/false."
},
"element": {
"type": "integer",
"minimum": 1,
"description": "The element's number from the last read or step answer."
}
},
"additionalProperties": false
},
"maxItems": 30,
"minItems": 1,
"description": "The fields in the order a person fills them."
},
"dialog_text": {
"type": "string",
"maxLength": 1000,
"description": "Text for a prompt dialog this step opens; implies accept."
}
},
"additionalProperties": false
},
"annotations": {
"title": "Fill in a form",
"readOnlyHint": false,
"openWorldHint": true,
"idempotentHint": false,
"destructiveHint": true
}
}Chooses `option` (its label as listed, or its value) in drop-down `element`. For a home-made drop-down, click it, then click the option. Answers the page after it: the elements and text in view, with the same numbers.
| Parameter | Type | Description |
|---|---|---|
| tab | string | The Tab id of the last answer. The step acts only while that tab is the shown one; if the user or another client showed another tab, it does nothing and answers tab_changed. Leave it out to act on the shown tab. |
| dialog | string | How to answer a native dialog (confirm, prompt, 'leave this page?') this step opens: accept presses OK, dismiss presses Cancel. Default: OK for an alert, Cancel for every other dialog. |
| option * | string | The option. |
| element * | integer | The element's number from the last read or step answer. |
| dialog_text | string | Text for a prompt dialog this step opens; implies accept. |
{
"name": "cotlet_browser_select",
"title": "Choose from a list",
"description": "Chooses `option` (its label as listed, or its value) in drop-down `element`. For a home-made drop-down, click it, then click the option. Answers the page after it: the elements and text in view, with the same numbers.",
"inputSchema": {
"type": "object",
"required": [
"element",
"option"
],
"properties": {
"tab": {
"type": "string",
"maxLength": 64,
"minLength": 1,
"description": "The Tab id of the last answer. The step acts only while that tab is the shown one; if the user or another client showed another tab, it does nothing and answers tab_changed. Leave it out to act on the shown tab."
},
"dialog": {
"enum": [
"accept",
"dismiss"
],
"type": "string",
"description": "How to answer a native dialog (confirm, prompt, 'leave this page?') this step opens: accept presses OK, dismiss presses Cancel. Default: OK for an alert, Cancel for every other dialog."
},
"option": {
"type": "string",
"maxLength": 300,
"description": "The option."
},
"element": {
"type": "integer",
"minimum": 1,
"description": "The element's number from the last read or step answer."
},
"dialog_text": {
"type": "string",
"maxLength": 1000,
"description": "Text for a prompt dialog this step opens; implies accept."
}
},
"additionalProperties": false
},
"annotations": {
"title": "Choose from a list",
"readOnlyHint": false,
"openWorldHint": true,
"idempotentHint": false,
"destructiveHint": true
}
}Presses a key on the focused element: Enter to send, Tab to the next field, Escape to close a pop-up, arrows in a list or slider, or one character (a site's shortcut). Answers the page after it: the elements and text in view, with the same numbers.
| Parameter | Type | Description |
|---|---|---|
| key * | string | One of Enter, Tab, Shift+Tab, Escape, Backspace, Delete, Space, ArrowDown, ArrowUp, ArrowLeft, ArrowRight, PageDown, PageUp, Home, End, or one character such as a or 5. |
| tab | string | The Tab id of the last answer. The step acts only while that tab is the shown one; if the user or another client showed another tab, it does nothing and answers tab_changed. Leave it out to act on the shown tab. |
| dialog | string | How to answer a native dialog (confirm, prompt, 'leave this page?') this step opens: accept presses OK, dismiss presses Cancel. Default: OK for an alert, Cancel for every other dialog. |
| repeat | integer | Times to press it. Default 1. |
| dialog_text | string | Text for a prompt dialog this step opens; implies accept. |
{
"name": "cotlet_browser_press",
"title": "Press a key",
"description": "Presses a key on the focused element: Enter to send, Tab to the next field, Escape to close a pop-up, arrows in a list or slider, or one character (a site's shortcut). Answers the page after it: the elements and text in view, with the same numbers.",
"inputSchema": {
"type": "object",
"required": [
"key"
],
"properties": {
"key": {
"type": "string",
"anyOf": [
{
"enum": [
"Enter",
"Tab",
"Shift+Tab",
"Escape",
"Backspace",
"Delete",
"Space",
"ArrowDown",
"ArrowUp",
"ArrowLeft",
"ArrowRight",
"PageDown",
"PageUp",
"Home",
"End"
]
},
{
"pattern": "^[ -~]$"
}
],
"description": "One of Enter, Tab, Shift+Tab, Escape, Backspace, Delete, Space, ArrowDown, ArrowUp, ArrowLeft, ArrowRight, PageDown, PageUp, Home, End, or one character such as a or 5."
},
"tab": {
"type": "string",
"maxLength": 64,
"minLength": 1,
"description": "The Tab id of the last answer. The step acts only while that tab is the shown one; if the user or another client showed another tab, it does nothing and answers tab_changed. Leave it out to act on the shown tab."
},
"dialog": {
"enum": [
"accept",
"dismiss"
],
"type": "string",
"description": "How to answer a native dialog (confirm, prompt, 'leave this page?') this step opens: accept presses OK, dismiss presses Cancel. Default: OK for an alert, Cancel for every other dialog."
},
"repeat": {
"type": "integer",
"maximum": 20,
"minimum": 1,
"description": "Times to press it. Default 1."
},
"dialog_text": {
"type": "string",
"maxLength": 1000,
"description": "Text for a prompt dialog this step opens; implies accept."
}
},
"additionalProperties": false
},
"annotations": {
"title": "Press a key",
"readOnlyHint": false,
"openWorldHint": true,
"idempotentHint": false,
"destructiveHint": true
}
}Puts files into file field or upload button `element`: each file is {"url": "https://..."} or {"file_id": "..."} of a file uploaded to Cotlet; up to 10 files, 20 MB each. Answers the page after it: the elements and text in view, with the same numbers.
| Parameter | Type | Description |
|---|---|---|
| tab | string | The Tab id of the last answer. The step acts only while that tab is the shown one; if the user or another client showed another tab, it does nothing and answers tab_changed. Leave it out to act on the shown tab. |
| files * | array | The files. |
| element * | integer | The element's number from the last read or step answer. |
{
"name": "cotlet_browser_upload",
"title": "Upload a file",
"description": "Puts files into file field or upload button `element`: each file is {\"url\": \"https://...\"} or {\"file_id\": \"...\"} of a file uploaded to Cotlet; up to 10 files, 20 MB each. Answers the page after it: the elements and text in view, with the same numbers.",
"inputSchema": {
"type": "object",
"required": [
"element",
"files"
],
"properties": {
"tab": {
"type": "string",
"maxLength": 64,
"minLength": 1,
"description": "The Tab id of the last answer. The step acts only while that tab is the shown one; if the user or another client showed another tab, it does nothing and answers tab_changed. Leave it out to act on the shown tab."
},
"files": {
"type": "array",
"items": {
"type": "object",
"properties": {
"url": {
"type": "string",
"format": "uri",
"description": "A public file URL."
},
"file_id": {
"type": "string",
"description": "A file uploaded to Cotlet."
}
},
"additionalProperties": false
},
"maxItems": 10,
"minItems": 1,
"description": "The files."
},
"element": {
"type": "integer",
"minimum": 1,
"description": "The element's number from the last read or step answer."
}
},
"additionalProperties": false
},
"annotations": {
"title": "Upload a file",
"readOnlyHint": false,
"openWorldHint": true,
"idempotentHint": false,
"destructiveHint": true
}
}Gets the file that clicking `element` (a download link or button) or opening `url` starts, also an image or PDF it only opens: answers its name, type, size and a link valid 15 minutes; CSV, JSON and other text files also as text.
| Parameter | Type | Description |
|---|---|---|
| tab | string | The Tab id of the last answer. The step acts only while that tab is the shown one; if the user or another client showed another tab, it does nothing and answers tab_changed. Leave it out to act on the shown tab. |
| url | string | A public http or https address, e.g. https://example.com. |
| element | integer | The element's number from the last read or step answer. |
{
"name": "cotlet_browser_download",
"title": "Download a file",
"description": "Gets the file that clicking `element` (a download link or button) or opening `url` starts, also an image or PDF it only opens: answers its name, type, size and a link valid 15 minutes; CSV, JSON and other text files also as text.",
"inputSchema": {
"type": "object",
"properties": {
"tab": {
"type": "string",
"maxLength": 64,
"minLength": 1,
"description": "The Tab id of the last answer. The step acts only while that tab is the shown one; if the user or another client showed another tab, it does nothing and answers tab_changed. Leave it out to act on the shown tab."
},
"url": {
"type": "string",
"format": "uri",
"description": "A public http or https address, e.g. https://example.com."
},
"element": {
"type": "integer",
"minimum": 1,
"description": "The element's number from the last read or step answer."
}
},
"additionalProperties": false
},
"annotations": {
"title": "Download a file",
"readOnlyHint": false,
"openWorldHint": true,
"idempotentHint": false,
"destructiveHint": true
}
}Runs a JavaScript function body on the page and answers what it returns, as JSON. Use it to extract data the page holds (a table, a list, attributes); act with the other tools. It cannot send requests, click, submit, or read cookies or storage; a filled field's value reads [hidden by Cotlet]. Example: return [...document.querySelectorAll('h2')].map(h => h.innerText)
| Parameter | Type | Description |
|---|---|---|
| tab | string | The Tab id of the last answer. The step acts only while that tab is the shown one; if the user or another client showed another tab, it does nothing and answers tab_changed. Leave it out to act on the shown tab. |
| script * | string | A function body that returns. |
{
"name": "cotlet_browser_evaluate",
"title": "Run a script on the page",
"description": "Runs a JavaScript function body on the page and answers what it returns, as JSON. Use it to extract data the page holds (a table, a list, attributes); act with the other tools. It cannot send requests, click, submit, or read cookies or storage; a filled field's value reads [hidden by Cotlet]. Example: return [...document.querySelectorAll('h2')].map(h => h.innerText)",
"inputSchema": {
"type": "object",
"required": [
"script"
],
"properties": {
"tab": {
"type": "string",
"maxLength": 64,
"minLength": 1,
"description": "The Tab id of the last answer. The step acts only while that tab is the shown one; if the user or another client showed another tab, it does nothing and answers tab_changed. Leave it out to act on the shown tab."
},
"script": {
"type": "string",
"maxLength": 20000,
"description": "A function body that returns."
}
},
"additionalProperties": false
},
"annotations": {
"title": "Run a script on the page",
"readOnlyHint": false,
"openWorldHint": true,
"idempotentHint": false,
"destructiveHint": true
}
}Waits until `text` shows on the page (at most `seconds`, default 5, up to 20), or just `seconds`: for results that load slowly. Says whether the text appeared. Answers the page after it: the elements and text in view, with the same numbers.
| Parameter | Type | Description |
|---|---|---|
| tab | string | The Tab id of the last answer. The step acts only while that tab is the shown one; if the user or another client showed another tab, it does nothing and answers tab_changed. Leave it out to act on the shown tab. |
| text | string | Text to wait for. |
| seconds | number | At most. |
{
"name": "cotlet_browser_wait",
"title": "Wait for the page",
"description": "Waits until `text` shows on the page (at most `seconds`, default 5, up to 20), or just `seconds`: for results that load slowly. Says whether the text appeared. Answers the page after it: the elements and text in view, with the same numbers.",
"inputSchema": {
"type": "object",
"properties": {
"tab": {
"type": "string",
"maxLength": 64,
"minLength": 1,
"description": "The Tab id of the last answer. The step acts only while that tab is the shown one; if the user or another client showed another tab, it does nothing and answers tab_changed. Leave it out to act on the shown tab."
},
"text": {
"type": "string",
"maxLength": 200,
"description": "Text to wait for."
},
"seconds": {
"type": "number",
"maximum": 20,
"description": "At most.",
"exclusiveMinimum": 0
}
},
"additionalProperties": false
},
"annotations": {
"title": "Wait for the page",
"readOnlyHint": true,
"openWorldHint": true,
"idempotentHint": true,
"destructiveHint": false
}
}Ends the browser session when the task is done: the browser keeps its cookies and sleeps, and the per-minute charge stops. Answers the session's minutes and credits.
No parameters.
{
"name": "cotlet_browser_close",
"title": "Close the browser",
"description": "Ends the browser session when the task is done: the browser keeps its cookies and sleeps, and the per-minute charge stops. Answers the session's minutes and credits.",
"inputSchema": {
"type": "object",
"properties": {},
"additionalProperties": false
},
"annotations": {
"title": "Close the browser",
"readOnlyHint": false,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}How to work in an app by clicking in the user's Cloud Browser with Cotlet's browser tools: which browser to use for this workspace and the sign-in link, the method step by step, the app's screens, menus and actions, notes, and the app's dedicated tools when Cotlet has them. Call it before the first browser step in an app. Works for any web app; one outside Cotlet's catalog gets the general method. Free, no browser session. For BrightLocal it covers these actions: List locations, Get rank tracker report, Get local search grid report, List reviews, Update rank tracker keywords, Re-run report.
| Parameter | Type | Description |
|---|---|---|
| app | string | The app's name or Cotlet slug. Default: BrightLocal. |
| task | string | What the user wants done in the app, in their words. |
{
"name": "cotlet_app_guide",
"title": "Cotlet: how to work in an app",
"description": "How to work in an app by clicking in the user's Cloud Browser with Cotlet's browser tools: which browser to use for this workspace and the sign-in link, the method step by step, the app's screens, menus and actions, notes, and the app's dedicated tools when Cotlet has them. Call it before the first browser step in an app. Works for any web app; one outside Cotlet's catalog gets the general method. Free, no browser session. For BrightLocal it covers these actions: List locations, Get rank tracker report, Get local search grid report, List reviews, Update rank tracker keywords, Re-run report.",
"inputSchema": {
"type": "object",
"properties": {
"app": {
"type": "string",
"maxLength": 120,
"description": "The app's name or Cotlet slug. Default: BrightLocal."
},
"task": {
"type": "string",
"maxLength": 500,
"description": "What the user wants done in the app, in their words."
}
},
"additionalProperties": false
},
"annotations": {
"title": "Cotlet: how to work in an app",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Read a Citation Tracker report: where the business is listed, missing, or listed with wrong NAP data. Returns the top-site coverage and citation score, name, address, postcode and phone accuracy counts, the competitors' citation counts and the citations themselves: site, type, authority, whether the business is listed and with which name, address and phone, the fields that do not match, duplicates and whether Citation Builder can submit to that site. Top sites first, then by authority.
| Parameter | Type | Description |
|---|---|---|
| limit | integer | Most citations returned, default 100. |
| filter | string | Which citations to return. Default all. |
| report_id * | integer | report_id from list_citation_tracker_reports. |
{
"name": "get_citation_tracker_report",
"title": "Get a Citation Tracker report",
"description": "Read a Citation Tracker report: where the business is listed, missing, or listed with wrong NAP data. Returns the top-site coverage and citation score, name, address, postcode and phone accuracy counts, the competitors' citation counts and the citations themselves: site, type, authority, whether the business is listed and with which name, address and phone, the fields that do not match, duplicates and whether Citation Builder can submit to that site. Top sites first, then by authority.",
"inputSchema": {
"type": "object",
"required": [
"report_id"
],
"properties": {
"limit": {
"type": "integer",
"maximum": 500,
"minimum": 1,
"description": "Most citations returned, default 100."
},
"filter": {
"enum": [
"all",
"listed",
"not_listed",
"nap_issues",
"top_sites_missing"
],
"type": "string",
"description": "Which citations to return. Default all."
},
"report_id": {
"type": "integer",
"minimum": 1,
"description": "report_id from list_citation_tracker_reports."
}
},
"additionalProperties": false
},
"annotations": {
"title": "Get a Citation Tracker report",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Read a location's Google Business Profile Audit: profile data, NAP check, local ranking factors. Returns the audited Google Business Profile (name, address, phone, website, category, description, verified, rating, reviews, photos, hours) and what changed since the last run, how the profile's name, address, postcode and phone match the location, local ranking factors, duplicates, recent reviews and, per keyword, the location's local rank with the top competitors. A location without a Google Business Profile has no audit: `audit` is null and `note` says what to set up.
| Parameter | Type | Description |
|---|---|---|
| location_id * | integer | location_id from list_locations. |
{
"name": "get_gbp_audit",
"title": "Get the Google Business Profile Audit",
"description": "Read a location's Google Business Profile Audit: profile data, NAP check, local ranking factors. Returns the audited Google Business Profile (name, address, phone, website, category, description, verified, rating, reviews, photos, hours) and what changed since the last run, how the profile's name, address, postcode and phone match the location, local ranking factors, duplicates, recent reviews and, per keyword, the location's local rank with the top competitors. A location without a Google Business Profile has no audit: `audit` is null and `note` says what to set up.",
"inputSchema": {
"type": "object",
"required": [
"location_id"
],
"properties": {
"location_id": {
"type": "integer",
"minimum": 1,
"description": "location_id from list_locations."
}
},
"additionalProperties": false
},
"annotations": {
"title": "Get the Google Business Profile Audit",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Read a location's Local Search Grid: the Google Maps rank at each grid point, and competitors. Returns the grid (size, points, distance, center), the average rank over all keywords, each keyword's latest run (average rank, points ranked 1-3, 4-10, 11+), and for one keyword and run (the first keyword and the latest run unless given) the rank at every grid point and the top 10 competitors. A location without a Google Business Profile has no grid: `report` is null and `note` says what to set up.
| Parameter | Type | Description |
|---|---|---|
| run_id | string | A run from the keyword's `runs`. Default: the latest. |
| keyword | string | A keyword of the report. Default: the first. |
| location_id * | integer | location_id from list_locations. |
{
"name": "get_local_search_grid_report",
"title": "Get a Local Search Grid report",
"description": "Read a location's Local Search Grid: the Google Maps rank at each grid point, and competitors. Returns the grid (size, points, distance, center), the average rank over all keywords, each keyword's latest run (average rank, points ranked 1-3, 4-10, 11+), and for one keyword and run (the first keyword and the latest run unless given) the rank at every grid point and the top 10 competitors. A location without a Google Business Profile has no grid: `report` is null and `note` says what to set up.",
"inputSchema": {
"type": "object",
"required": [
"location_id"
],
"properties": {
"run_id": {
"type": "string",
"maxLength": 64,
"description": "A run from the keyword's `runs`. Default: the latest."
},
"keyword": {
"type": "string",
"maxLength": 200,
"description": "A keyword of the report. Default: the first."
},
"location_id": {
"type": "integer",
"minimum": 1,
"description": "location_id from list_locations."
}
},
"additionalProperties": false
},
"annotations": {
"title": "Get a Local Search Grid report",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Read one location's business details: name, address, phone, website, category, hours, descriptions. Returns the record BrightLocal compares citations and listings against (NAP): business name, address, phones, website, category, contact person, short and long description, year founded, employees, payment methods, services and opening hours.
| Parameter | Type | Description |
|---|---|---|
| location_id * | integer | location_id from list_locations. |
{
"name": "get_location",
"title": "Get a location",
"description": "Read one location's business details: name, address, phone, website, category, hours, descriptions. Returns the record BrightLocal compares citations and listings against (NAP): business name, address, phones, website, category, contact person, short and long description, year founded, employees, payment methods, services and opening hours.",
"inputSchema": {
"type": "object",
"required": [
"location_id"
],
"properties": {
"location_id": {
"type": "integer",
"minimum": 1,
"description": "location_id from list_locations."
}
},
"additionalProperties": false
},
"annotations": {
"title": "Get a location",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Read a Rank Tracker report: each keyword's position on Google, Maps and the local pack, with changes. Returns one run of the report (the latest unless run_id is given) against the run before it: per keyword the search volume and, per search engine, the rank (null = not in the top 50), previous rank, change and ranking URL; the keywords up, down, gained and lost; the competitors tracked. `runs` lists every run.
| Parameter | Type | Description |
|---|---|---|
| run_id | integer | A run from `runs`. Default: the latest. |
| report_id * | integer | report_id from list_rank_tracker_reports. |
| location_id * | integer | location_id of the report, from list_rank_tracker_reports. |
{
"name": "get_rank_tracker_report",
"title": "Get a rank tracker report",
"description": "Read a Rank Tracker report: each keyword's position on Google, Maps and the local pack, with changes. Returns one run of the report (the latest unless run_id is given) against the run before it: per keyword the search volume and, per search engine, the rank (null = not in the top 50), previous rank, change and ranking URL; the keywords up, down, gained and lost; the competitors tracked. `runs` lists every run.",
"inputSchema": {
"type": "object",
"required": [
"report_id",
"location_id"
],
"properties": {
"run_id": {
"type": "integer",
"minimum": 1,
"description": "A run from `runs`. Default: the latest."
},
"report_id": {
"type": "integer",
"minimum": 1,
"description": "report_id from list_rank_tracker_reports."
},
"location_id": {
"type": "integer",
"minimum": 1,
"description": "location_id of the report, from list_rank_tracker_reports."
}
},
"additionalProperties": false
},
"annotations": {
"title": "Get a rank tracker report",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Read a location's star rating and review counts overall and per review site. Returns the average star rating and total reviews over all tracked sites, the count per star rating, and per site with a listing: its rating, total, new reviews, reviews in the last 30 days, this and last month and this year, and the profile link. A location without a Reputation Manager report (BrightLocal Grow plan) answers zeros and a note.
| Parameter | Type | Description |
|---|---|---|
| location_id * | integer | location_id from list_locations. |
{
"name": "get_review_summary",
"title": "Get the review summary",
"description": "Read a location's star rating and review counts overall and per review site. Returns the average star rating and total reviews over all tracked sites, the count per star rating, and per site with a listing: its rating, total, new reviews, reviews in the last 30 days, this and last month and this year, and the profile link. A location without a Reputation Manager report (BrightLocal Grow plan) answers zeros and a note.",
"inputSchema": {
"type": "object",
"required": [
"location_id"
],
"properties": {
"location_id": {
"type": "integer",
"minimum": 1,
"description": "location_id from list_locations."
}
},
"additionalProperties": false
},
"annotations": {
"title": "Get the review summary",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}List Active Sync alerts: changes found on a location's listings on other sites. Each alert is a field (name, address, phone, website, category, description) whose value on an external listing (Google Business Profile, Facebook, Bing, Apple Maps, Yelp) differs from the location's data in BrightLocal. Alerts appear only for locations with Active Sync connections. new_alerts counts the unseen ones.
| Parameter | Type | Description |
|---|---|---|
| query | string | Location name to search for. |
| cursor | string | next_cursor from the previous call. |
{
"name": "list_active_sync_alerts",
"title": "List Active Sync alerts",
"description": "List Active Sync alerts: changes found on a location's listings on other sites. Each alert is a field (name, address, phone, website, category, description) whose value on an external listing (Google Business Profile, Facebook, Bing, Apple Maps, Yelp) differs from the location's data in BrightLocal. Alerts appear only for locations with Active Sync connections. new_alerts counts the unseen ones.",
"inputSchema": {
"type": "object",
"properties": {
"query": {
"type": "string",
"maxLength": 100,
"description": "Location name to search for."
},
"cursor": {
"type": "string",
"description": "next_cursor from the previous call."
}
},
"additionalProperties": false
},
"annotations": {
"title": "List Active Sync alerts",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}List Citation Builder campaigns with their status, from Saved to Submitting To Sites and Complete. One row per campaign: location, status (Saved, Reviewing Data, On Hold, Submitting To Sites, Live Listing Checks, Complete), payment date, number of listings ordered, data aggregators and alerts. Saved campaigns are not paid or submitted yet. location_id filters each page after BrightLocal returns it, so a page can come back short while next_cursor continues; total counts all campaigns.
| Parameter | Type | Description |
|---|---|---|
| cursor | string | next_cursor from the previous call. |
| status | string | Only campaigns in this status. |
| location_id | integer | Only campaigns of this location. |
{
"name": "list_citation_builder_campaigns",
"title": "List Citation Builder campaigns",
"description": "List Citation Builder campaigns with their status, from Saved to Submitting To Sites and Complete. One row per campaign: location, status (Saved, Reviewing Data, On Hold, Submitting To Sites, Live Listing Checks, Complete), payment date, number of listings ordered, data aggregators and alerts. Saved campaigns are not paid or submitted yet. location_id filters each page after BrightLocal returns it, so a page can come back short while next_cursor continues; total counts all campaigns.",
"inputSchema": {
"type": "object",
"properties": {
"cursor": {
"type": "string",
"description": "next_cursor from the previous call."
},
"status": {
"enum": [
"Saved",
"Reviewing Data",
"On Hold",
"Submitting To Sites",
"Live Listing Checks",
"Complete"
],
"type": "string",
"description": "Only campaigns in this status."
},
"location_id": {
"type": "integer",
"minimum": 1,
"description": "Only campaigns of this location."
}
},
"additionalProperties": false
},
"annotations": {
"title": "List Citation Builder campaigns",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}List Citation Tracker reports with their last run, live citations and competitor citations. One row per report: location, reference, schedule, last run, the number of live citations (found and indexed by Google) and of competitor citations (sites your competitors are listed on). Read a report with get_citation_tracker_report. 20 per page. location_id filters each page after BrightLocal returns it, so a page can come back short while next_cursor continues.
| Parameter | Type | Description |
|---|---|---|
| cursor | string | next_cursor from the previous call. |
| location_id | integer | Only reports of this location. |
{
"name": "list_citation_tracker_reports",
"title": "List Citation Tracker reports",
"description": "List Citation Tracker reports with their last run, live citations and competitor citations. One row per report: location, reference, schedule, last run, the number of live citations (found and indexed by Google) and of competitor citations (sites your competitors are listed on). Read a report with get_citation_tracker_report. 20 per page. location_id filters each page after BrightLocal returns it, so a page can come back short while next_cursor continues.",
"inputSchema": {
"type": "object",
"properties": {
"cursor": {
"type": "string",
"description": "next_cursor from the previous call."
},
"location_id": {
"type": "integer",
"minimum": 1,
"description": "Only reports of this location."
}
},
"additionalProperties": false
},
"annotations": {
"title": "List Citation Tracker reports",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}List Local Search Grid reports: keywords, grid size and the average Google Maps rank across the grid. One row per report: location, keywords, schedule, last run, status, grid size and points, average rank over all keywords and its change, credits a manual re-run costs. Local Search Grid needs the location's Google Business Profile, so locations without one have no rows. location_id filters each page after BrightLocal returns it, so a page can come back short while next_cursor continues. Read a grid with get_local_search_grid_report.
| Parameter | Type | Description |
|---|---|---|
| cursor | string | next_cursor from the previous call. |
| location_id | integer | Only reports of this location. |
{
"name": "list_local_search_grid_reports",
"title": "List Local Search Grid reports",
"description": "List Local Search Grid reports: keywords, grid size and the average Google Maps rank across the grid. One row per report: location, keywords, schedule, last run, status, grid size and points, average rank over all keywords and its change, credits a manual re-run costs. Local Search Grid needs the location's Google Business Profile, so locations without one have no rows. location_id filters each page after BrightLocal returns it, so a page can come back short while next_cursor continues. Read a grid with get_local_search_grid_report.",
"inputSchema": {
"type": "object",
"properties": {
"cursor": {
"type": "string",
"description": "next_cursor from the previous call."
},
"location_id": {
"type": "integer",
"minimum": 1,
"description": "Only reports of this location."
}
},
"additionalProperties": false
},
"annotations": {
"title": "List Local Search Grid reports",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}List the locations in the account with their rank, citation and review metrics, as on All Locations. Returns each location with its location_id, name, reference, city, status (active or ad_hoc) and the metrics of the All Locations page: average Google position and its change, rankings up, down and new, Local Search Grid average, citation score, live citations, star rating, total and recent reviews, Active Sync alerts. `reports` says which tools have a report on the location. 50 per page.
| Parameter | Type | Description |
|---|---|---|
| query | string | Business name, reference or zip code to search for. |
| cursor | string | next_cursor from the previous call. |
| status | string | Only locations in this state. Default: active and ad_hoc. |
{
"name": "list_locations",
"title": "List locations",
"description": "List the locations in the account with their rank, citation and review metrics, as on All Locations. Returns each location with its location_id, name, reference, city, status (active or ad_hoc) and the metrics of the All Locations page: average Google position and its change, rankings up, down and new, Local Search Grid average, citation score, live citations, star rating, total and recent reviews, Active Sync alerts. `reports` says which tools have a report on the location. 50 per page.",
"inputSchema": {
"type": "object",
"properties": {
"query": {
"type": "string",
"maxLength": 100,
"description": "Business name, reference or zip code to search for."
},
"cursor": {
"type": "string",
"description": "next_cursor from the previous call."
},
"status": {
"enum": [
"active",
"ad_hoc",
"archived"
],
"type": "string",
"description": "Only locations in this state. Default: active and ad_hoc."
}
},
"additionalProperties": false
},
"annotations": {
"title": "List locations",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}List Rank Tracker reports with their latest run and average Google position. One row per report: location, schedule (ad_hoc, weekly, monthly), date of the latest run, status, average Google position and its change, keywords and positions moved. average_google_position is null when no keyword ranks in the top 50. location_id filters each page after BrightLocal returns it, so a page can come back short while next_cursor continues; total counts all reports. Read a report with get_rank_tracker_report and its location_id.
| Parameter | Type | Description |
|---|---|---|
| cursor | string | next_cursor from the previous call. |
| location_id | integer | Only reports of this location. |
{
"name": "list_rank_tracker_reports",
"title": "List rank tracker reports",
"description": "List Rank Tracker reports with their latest run and average Google position. One row per report: location, schedule (ad_hoc, weekly, monthly), date of the latest run, status, average Google position and its change, keywords and positions moved. average_google_position is null when no keyword ranks in the top 50. location_id filters each page after BrightLocal returns it, so a page can come back short while next_cursor continues; total counts all reports. Read a report with get_rank_tracker_report and its location_id.",
"inputSchema": {
"type": "object",
"properties": {
"cursor": {
"type": "string",
"description": "next_cursor from the previous call."
},
"location_id": {
"type": "integer",
"minimum": 1,
"description": "Only reports of this location."
}
},
"additionalProperties": false
},
"annotations": {
"title": "List rank tracker reports",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}List a location's reviews from all tracked review sites, newest first, with rating, text and status. Returns reviews Reputation Manager collected for the location: date, star rating, reviewer, site, text, status (unread, action_required, do_not_respond, manually_responded, auto_responded, pending_removal, successfully_removed, removal_failed) and whether BrightLocal can post a reply (can_reply, needs a connected Google Business Profile or Facebook page). Filter by rating and site. A location without a Reputation Manager report (BrightLocal Grow plan, with the Google Business Profile or Facebook page connected) answers an empty list and a note.
| Parameter | Type | Description |
|---|---|---|
| limit | integer | Reviews per page, default 25. |
| cursor | string | next_cursor from the previous call. |
| rating | array | Only reviews with these star ratings, e.g. [1, 2]. |
| source | string | Only this review site, e.g. google, yelp, facebook. |
| location_id * | integer | location_id from list_locations. |
{
"name": "list_reviews",
"title": "List reviews",
"description": "List a location's reviews from all tracked review sites, newest first, with rating, text and status. Returns reviews Reputation Manager collected for the location: date, star rating, reviewer, site, text, status (unread, action_required, do_not_respond, manually_responded, auto_responded, pending_removal, successfully_removed, removal_failed) and whether BrightLocal can post a reply (can_reply, needs a connected Google Business Profile or Facebook page). Filter by rating and site. A location without a Reputation Manager report (BrightLocal Grow plan, with the Google Business Profile or Facebook page connected) answers an empty list and a note.",
"inputSchema": {
"type": "object",
"required": [
"location_id"
],
"properties": {
"limit": {
"type": "integer",
"maximum": 100,
"minimum": 1,
"description": "Reviews per page, default 25."
},
"cursor": {
"type": "string",
"description": "next_cursor from the previous call."
},
"rating": {
"type": "array",
"items": {
"type": "integer",
"maximum": 5,
"minimum": 1
},
"maxItems": 5,
"description": "Only reviews with these star ratings, e.g. [1, 2]."
},
"source": {
"type": "string",
"maxLength": 50,
"description": "Only this review site, e.g. google, yelp, facebook."
},
"location_id": {
"type": "integer",
"minimum": 1,
"description": "location_id from list_locations."
}
},
"additionalProperties": false
},
"annotations": {
"title": "List reviews",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Run one of a location's reports now, as the Re-run button does. Starts a manual run of the location's report of that type, as the Re-run button does. A manual run uses one of the account's ad-hoc run credits; a Local Search Grid run also uses grid credits. After a trial ends BrightLocal stops runs. local_search_grid and gbp_audit need the location's Google Business Profile, reputation_manager needs Reputation Manager (Grow plan); without them the call is refused with the reason. The run takes minutes; read the report afterwards.
| Parameter | Type | Description |
|---|---|---|
| location_id * | integer | location_id from list_locations. |
| report_type * | string | Which of the location's reports to run. |
{
"name": "rerun_report",
"title": "Re-run a report",
"description": "Run one of a location's reports now, as the Re-run button does. Starts a manual run of the location's report of that type, as the Re-run button does. A manual run uses one of the account's ad-hoc run credits; a Local Search Grid run also uses grid credits. After a trial ends BrightLocal stops runs. local_search_grid and gbp_audit need the location's Google Business Profile, reputation_manager needs Reputation Manager (Grow plan); without them the call is refused with the reason. The run takes minutes; read the report afterwards.",
"inputSchema": {
"type": "object",
"required": [
"location_id",
"report_type"
],
"properties": {
"location_id": {
"type": "integer",
"minimum": 1,
"description": "location_id from list_locations."
},
"report_type": {
"enum": [
"rank_tracker",
"citation_tracker",
"local_search_grid",
"reputation_manager",
"gbp_audit"
],
"type": "string",
"description": "Which of the location's reports to run."
}
},
"additionalProperties": false
},
"annotations": {
"title": "Re-run a report",
"readOnlyHint": false,
"openWorldHint": true,
"idempotentHint": false,
"destructiveHint": true
}
}Post a public reply to a review on Google or Facebook through BrightLocal. Publishes the text as the business's reply under the review on its site and marks the review Manually Responded. Only reviews with can_reply true in list_reviews accept a reply: the location needs a connected Google Business Profile or Facebook page. The reviewer and anyone reading the review see it. The review must be among the location's latest 1000. Waits for the owner's approval.
| Parameter | Type | Description |
|---|---|---|
| text * | string | The public reply. |
| review_id * | integer | review_id from list_reviews. |
| location_id * | integer | location_id from list_locations. |
{
"name": "respond_to_review",
"title": "Reply to a review",
"description": "Post a public reply to a review on Google or Facebook through BrightLocal. Publishes the text as the business's reply under the review on its site and marks the review Manually Responded. Only reviews with can_reply true in list_reviews accept a reply: the location needs a connected Google Business Profile or Facebook page. The reviewer and anyone reading the review see it. The review must be among the location's latest 1000. Waits for the owner's approval.",
"inputSchema": {
"type": "object",
"required": [
"location_id",
"review_id",
"text"
],
"properties": {
"text": {
"type": "string",
"maxLength": 4000,
"minLength": 1,
"description": "The public reply."
},
"review_id": {
"type": "integer",
"minimum": 1,
"description": "review_id from list_reviews."
},
"location_id": {
"type": "integer",
"minimum": 1,
"description": "location_id from list_locations."
}
},
"additionalProperties": false
},
"annotations": {
"title": "Reply to a review",
"readOnlyHint": false,
"openWorldHint": true,
"idempotentHint": false,
"destructiveHint": true
}
}Add or remove keywords tracked by a location's Rank Tracker report. Changes the keyword list of the location's Rank Tracker report and saves the report with its other settings unchanged. Up to 100 keywords per report. Keywords already tracked are not added twice. New keywords get positions on the next scheduled run, or now with rerun_report.
| Parameter | Type | Description |
|---|---|---|
| add | array | Keywords to start tracking. |
| remove | array | Keywords to stop tracking. |
| location_id * | integer | location_id of the Rank Tracker report. |
{
"name": "update_rank_tracker_keywords",
"title": "Update rank tracker keywords",
"description": "Add or remove keywords tracked by a location's Rank Tracker report. Changes the keyword list of the location's Rank Tracker report and saves the report with its other settings unchanged. Up to 100 keywords per report. Keywords already tracked are not added twice. New keywords get positions on the next scheduled run, or now with rerun_report.",
"inputSchema": {
"type": "object",
"required": [
"location_id"
],
"properties": {
"add": {
"type": "array",
"items": {
"type": "string",
"maxLength": 150,
"minLength": 1
},
"maxItems": 100,
"description": "Keywords to start tracking."
},
"remove": {
"type": "array",
"items": {
"type": "string",
"maxLength": 150,
"minLength": 1
},
"maxItems": 100,
"description": "Keywords to stop tracking."
},
"location_id": {
"type": "integer",
"minimum": 1,
"description": "location_id of the Rank Tracker report."
}
},
"minProperties": 2,
"additionalProperties": false
},
"annotations": {
"title": "Update rank tracker keywords",
"readOnlyHint": false,
"openWorldHint": true,
"idempotentHint": false,
"destructiveHint": true
}
}List locations in the user's own BrightLocal account from ChatGPT, Claude or any AI agent. Returns how to do it in BrightLocal step by step (screens, buttons, fields) and opens nothing by itself; then do it with the cotlet_browser_* tools in the user's BrightLocal Cloud Browser. BrightLocal's official API: BrightLocal has a REST API and an official MCP server, BrightLocal Anywhere.
No parameters.
{
"name": "brightlocal_list_locations",
"title": "List locations in BrightLocal",
"description": "List locations in the user's own BrightLocal account from ChatGPT, Claude or any AI agent. Returns how to do it in BrightLocal step by step (screens, buttons, fields) and opens nothing by itself; then do it with the cotlet_browser_* tools in the user's BrightLocal Cloud Browser. BrightLocal's official API: BrightLocal has a REST API and an official MCP server, BrightLocal Anywhere.",
"inputSchema": {
"type": "object",
"properties": {},
"additionalProperties": false
},
"annotations": {
"title": "List locations in BrightLocal",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Get rank tracker report in the user's own BrightLocal account from ChatGPT, Claude or any AI agent. Returns how to do it in BrightLocal step by step (screens, buttons, fields) and opens nothing by itself; then do it with the cotlet_browser_* tools in the user's BrightLocal Cloud Browser. BrightLocal's official API: BrightLocal has a REST API and an official MCP server, BrightLocal Anywhere.
No parameters.
{
"name": "brightlocal_get_rank_tracker_report",
"title": "Get rank tracker report in BrightLocal",
"description": "Get rank tracker report in the user's own BrightLocal account from ChatGPT, Claude or any AI agent. Returns how to do it in BrightLocal step by step (screens, buttons, fields) and opens nothing by itself; then do it with the cotlet_browser_* tools in the user's BrightLocal Cloud Browser. BrightLocal's official API: BrightLocal has a REST API and an official MCP server, BrightLocal Anywhere.",
"inputSchema": {
"type": "object",
"properties": {},
"additionalProperties": false
},
"annotations": {
"title": "Get rank tracker report in BrightLocal",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Get local search grid report in the user's own BrightLocal account from ChatGPT, Claude or any AI agent. Returns how to do it in BrightLocal step by step (screens, buttons, fields) and opens nothing by itself; then do it with the cotlet_browser_* tools in the user's BrightLocal Cloud Browser. BrightLocal's official API: BrightLocal has a REST API and an official MCP server, BrightLocal Anywhere.
No parameters.
{
"name": "brightlocal_get_local_search_grid_report",
"title": "Get local search grid report in BrightLocal",
"description": "Get local search grid report in the user's own BrightLocal account from ChatGPT, Claude or any AI agent. Returns how to do it in BrightLocal step by step (screens, buttons, fields) and opens nothing by itself; then do it with the cotlet_browser_* tools in the user's BrightLocal Cloud Browser. BrightLocal's official API: BrightLocal has a REST API and an official MCP server, BrightLocal Anywhere.",
"inputSchema": {
"type": "object",
"properties": {},
"additionalProperties": false
},
"annotations": {
"title": "Get local search grid report in BrightLocal",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}List reviews in the user's own BrightLocal account from ChatGPT, Claude or any AI agent. Returns how to do it in BrightLocal step by step (screens, buttons, fields) and opens nothing by itself; then do it with the cotlet_browser_* tools in the user's BrightLocal Cloud Browser. BrightLocal's official API: BrightLocal has a REST API and an official MCP server, BrightLocal Anywhere.
No parameters.
{
"name": "brightlocal_list_reviews",
"title": "List reviews in BrightLocal",
"description": "List reviews in the user's own BrightLocal account from ChatGPT, Claude or any AI agent. Returns how to do it in BrightLocal step by step (screens, buttons, fields) and opens nothing by itself; then do it with the cotlet_browser_* tools in the user's BrightLocal Cloud Browser. BrightLocal's official API: BrightLocal has a REST API and an official MCP server, BrightLocal Anywhere.",
"inputSchema": {
"type": "object",
"properties": {},
"additionalProperties": false
},
"annotations": {
"title": "List reviews in BrightLocal",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Update rank tracker keywords in the user's own BrightLocal account from ChatGPT, Claude or any AI agent. Returns how to do it in BrightLocal step by step (screens, buttons, fields) and opens nothing by itself; then do it with the cotlet_browser_* tools in the user's BrightLocal Cloud Browser. BrightLocal's official API: BrightLocal has a REST API and an official MCP server, BrightLocal Anywhere.
No parameters.
{
"name": "brightlocal_update_rank_tracker_keywords",
"title": "Update rank tracker keywords in BrightLocal",
"description": "Update rank tracker keywords in the user's own BrightLocal account from ChatGPT, Claude or any AI agent. Returns how to do it in BrightLocal step by step (screens, buttons, fields) and opens nothing by itself; then do it with the cotlet_browser_* tools in the user's BrightLocal Cloud Browser. BrightLocal's official API: BrightLocal has a REST API and an official MCP server, BrightLocal Anywhere.",
"inputSchema": {
"type": "object",
"properties": {},
"additionalProperties": false
},
"annotations": {
"title": "Update rank tracker keywords in BrightLocal",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Re-run report in the user's own BrightLocal account from ChatGPT, Claude or any AI agent. Returns how to do it in BrightLocal step by step (screens, buttons, fields) and opens nothing by itself; then do it with the cotlet_browser_* tools in the user's BrightLocal Cloud Browser. BrightLocal's official API: BrightLocal has a REST API and an official MCP server, BrightLocal Anywhere.
No parameters.
{
"name": "brightlocal_re_run_report",
"title": "Re-run report in BrightLocal",
"description": "Re-run report in the user's own BrightLocal account from ChatGPT, Claude or any AI agent. Returns how to do it in BrightLocal step by step (screens, buttons, fields) and opens nothing by itself; then do it with the cotlet_browser_* tools in the user's BrightLocal Cloud Browser. BrightLocal's official API: BrightLocal has a REST API and an official MCP server, BrightLocal Anywhere.",
"inputSchema": {
"type": "object",
"properties": {},
"additionalProperties": false
},
"annotations": {
"title": "Re-run report in BrightLocal",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}BrightLocal MCP server by Cotlet: connects BrightLocal to Claude Code, ChatGPT and any AI agent. Cotlet works in the user's own BrightLocal account through their Cloud Browser, a real Chrome hosted by Cotlet where the user signed in to BrightLocal themselves; Cotlet does not store their password. The brightlocal_* tools each return the BrightLocal steps for one action (screens, buttons, fields) and open nothing: call one, then do the steps with the cotlet_browser_* tools. Each BrightLocal operation is its own tool and does a job in one call: prefer them. Writes that reach other people wait for the user's approval in the Cotlet console and answer with status pending and a call_id, which cotlet_get_call reports on. Several BrightLocal accounts: pass `browser` with a name cotlet_apps lists. For what the operations do not cover, the cotlet_browser_* tools work in the same BrightLocal browser: call cotlet_app_guide first (free) for its screens. Call the browser tools one at a time, never in parallel: wait for each answer. Open the page with cotlet_browser_open, then cotlet_browser_read it once for its text and numbered elements. Act on those numbers with click, type, select and press, or fill_form for several fields at once; each action answers the page after it (the elements and text in view, same numbers), so read again only to see the whole page. cotlet_browser_find finds one thing on a long page; scroll loads lists that grow as you scroll; screenshot shows boards and canvases (click or drag them by x, y); download gets a file; evaluate extracts data with a script. Public pages open without signing in. Signing in for the user is allowed: on a sign-in page or a 2FA prompt, type the email, password and code the user gave you, and ask them for what you lack (Cotlet does not store them). If the user would rather sign in themselves, or a check a step says needs the person, give them one link only, the sign-in link from cotlet_app_guide (it opens their Cloud Browser right on that page), ask them to reply "done", then go on with the task. Ask the user before a step that sends, publishes, deletes or pays. Each answer names its Tab: send that id as `tab` with the next steps, so a step never acts on another tab the user or another client showed meanwhile (it does nothing and answers tab_changed: read the shown tab or switch back). A refusal says how to go on: no_tab, list the tabs, switch to the task's site (or reopen it), read it and use the fresh Tab id and element numbers; no_element, find the control by its label in the page shown, or read again, and fill only the fields not yet filled; script_failed, read the error and the page first, fix an invalid script, never send it unchanged. Close the browser with cotlet_browser_close when done: each started minute of a session uses credits. After each finished task, never in the middle of one, give the result, then offer 2 or 3 next things to do in the app, from the guide's "What to offer next": another read first, then a small change you make only after the user says yes, and an automation when a job repeats. If you cannot finish the task in the browser (an element you cannot find, a page that will not work, a flow you do not understand) or a step keeps failing, call cotlet_report_issue with what the user asked, the page, the step and what you saw. cotlet_whoami names the account and its credits, cotlet_apps whether the app is ready. When a Cotlet answer starts with a note that your Cotlet tool list is old, tell the user first, with its link, and call cotlet_refresh_button if you have it. The account and credits: https://cotlet.dev/app.
Names, descriptions and schemas were written by the server and are shown as data.
Pattern matches on what the server declares. They show what it says it can do, not what it does.
None yet. Changes appear after a server's second daily check.
{
"name": "cotlet_report_issue",
"title": "Cotlet: report a bug or a missing feature",
"description": "Sends a report to the Cotlet team: a tool that failed or returned wrong data, an error you could not get past, or a step the browser could not do, with the page, the step and what you saw. A missing dedicated tool is not a problem to report: do the task in the browser. A feature the user asks for goes as feature_request. A report promises nothing: tell the user it was sent, never that something will be built or fixed, or when. The report carries the error text and call_id when there is one, never passwords or tokens. Needs the user's Cotlet API key or sign-in.",
"inputSchema": {
"type": "object",
"title": "AgentReportCreate",
"required": [
"kind",
"title",
"description"
],
"properties": {
"app": {
"anyOf": [
{
"type": "string",
"maxLength": 80
},
{
"type": "null"
}
],
"title": "App",
"default": null,
"description": "App slug the report is about, e.g. 'skool', or for a site in the web browser its host, e.g. 'app.example.com'."
},
"kind": {
"enum": [
"bug",
"error",
"feature_request",
"missing_feature",
"other"
],
"type": "string",
"title": "Kind",
"description": "bug: a tool did the wrong thing or returned wrong data. error: a call failed or returned an error you could not get past. feature_request: something new the user asked for. missing_feature: a step the task needed that you tried and could not do, in the browser or with a tool. other: anything else."
},
"tool": {
"anyOf": [
{
"type": "string",
"maxLength": 160
},
{
"type": "null"
}
],
"title": "Tool",
"default": null,
"description": "Tool or endpoint name, e.g. 'skool_list_members'."
},
"title": {
"type": "string",
"title": "Title",
"maxLength": 200,
"minLength": 3,
"description": "One line, e.g. 'skool_list_members stops after 50 members'."
},
"client": {
"anyOf": [
{
"type": "string",
"maxLength": 80
},
{
"type": "null"
}
],
"title": "Client",
"default": null,
"description": "Agent or tool sending this, e.g. 'Claude Code'."
},
"call_id": {
"anyOf": [
{
"type": "string",
"format": "uuid"
},
{
"type": "null"
}
],
"title": "Call Id",
"default": null,
"description": "call_id of the call that went wrong, if any."
},
"description": {
"type": "string",
"title": "Description",
"maxLength": 5000,
"minLength": 10,
"description": "What the user asked for, what you tried, what you expected and what happened, with the error text if there was one. No passwords, tokens or other secrets."
}
},
"description": "Body of POST /api/v1/reports and the arguments of the MCP tool cotlet_report_issue.",
"additionalProperties": false
},
"annotations": {
"title": "Cotlet: report a bug or a missing feature",
"readOnlyHint": false,
"openWorldHint": false,
"idempotentHint": false,
"destructiveHint": false
}
}{
"name": "cotlet_browser_click",
"title": "Click on the page",
"description": "Clicks element `element`, or point `x`, `y` of the screenshot; `double` double-clicks, `button: right` right-clicks. Answers the page after it: the elements and text in view, with the same numbers. Says when nothing changed. A link that would open a new tab opens in this one. Buttons that pay or buy, and sign-in and account pages, are refused.",
"inputSchema": {
"type": "object",
"properties": {
"x": {
"type": "number",
"minimum": 0,
"description": "Instead of `element`: pixels from the left of the screenshot."
},
"y": {
"type": "number",
"minimum": 0,
"description": "With `x`: pixels from the top of the screenshot."
},
"tab": {
"type": "string",
"maxLength": 64,
"minLength": 1,
"description": "The Tab id of the last answer. The step acts only while that tab is the shown one; if the user or another client showed another tab, it does nothing and answers tab_changed. Leave it out to act on the shown tab."
},
"button": {
"enum": [
"left",
"right"
],
"type": "string",
"description": "right opens the page's own context menu. Default: left."
},
"dialog": {
"enum": [
"accept",
"dismiss"
],
"type": "string",
"description": "How to answer a native dialog (confirm, prompt, 'leave this page?') this step opens: accept presses OK, dismiss presses Cancel. Default: OK for an alert, Cancel for every other dialog."
},
"double": {
"type": "boolean",
"description": "Double-click."
},
"element": {
"type": "integer",
"minimum": 1,
"description": "The element's number from the last read or step answer."
},
"dialog_text": {
"type": "string",
"maxLength": 1000,
"description": "Text for a prompt dialog this step opens; implies accept."
}
},
"additionalProperties": false
},
"annotations": {
"title": "Click on the page",
"readOnlyHint": false,
"openWorldHint": true,
"idempotentHint": false,
"destructiveHint": true
}
}| Text for a prompt dialog this step opens; implies accept. |
{
"name": "cotlet_browser_type",
"title": "Type on the page",
"description": "Types `text` into field `element`, replacing what it held; `submit` presses Enter after it. For several fields use fill_form. Without `element` the text goes where the focus is, as a person types after clicking: for spreadsheet cells and editors that read does not number (Google Sheets, Docs), click the place first; there a tab in `text` presses Tab and a line break Enter, so one call fills a table. Answers the page after it: the elements and text in view, with the same numbers. A password or code the user gave you goes in like any text; card fields are refused.",
"inputSchema": {
"type": "object",
"required": [
"text"
],
"properties": {
"tab": {
"type": "string",
"maxLength": 64,
"minLength": 1,
"description": "The Tab id of the last answer. The step acts only while that tab is the shown one; if the user or another client showed another tab, it does nothing and answers tab_changed. Leave it out to act on the shown tab."
},
"text": {
"type": "string",
"maxLength": 5000,
"description": "The text to type."
},
"dialog": {
"enum": [
"accept",
"dismiss"
],
"type": "string",
"description": "How to answer a native dialog (confirm, prompt, 'leave this page?') this step opens: accept presses OK, dismiss presses Cancel. Default: OK for an alert, Cancel for every other dialog."
},
"slowly": {
"type": "boolean",
"description": "Key by key, for a search or address field whose suggestions do not appear."
},
"submit": {
"type": "boolean",
"description": "Press Enter after typing, e.g. to search."
},
"element": {
"type": "integer",
"minimum": 1,
"description": "The field's number from the last read. Leave it out to type where the focus is."
},
"dialog_text": {
"type": "string",
"maxLength": 1000,
"description": "Text for a prompt dialog this step opens; implies accept."
}
},
"additionalProperties": false
},
"annotations": {
"title": "Type on the page",
"readOnlyHint": false,
"openWorldHint": true,
"idempotentHint": false,
"destructiveHint": true
}
}