com.scriptmasterlabs/agent-browser is an MCP server published by com.scriptmasterlabs, hosted at agent-browser-r7d2.onrender.com. When last checked on 2026-11-22 it was working: it answers and lists its tools. It declares 6 tools, including browser_navigate, browser_extract, browser_snapshot, browser_act, browser_screenshot.
Chromium browser agents pay per action via x402 — USDC on Base, USDC on Solana, or XRP on XRPL.
645 connections through 5 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.
Use for: loading a web page in a real Chromium browser and reading it. Returns the page title, final URL and a clean text extract (up to 8000 chars). Don't use when: you only need raw HTML or an API response — a plain HTTP fetch is cheaper. Errors are structured: NAV_TIMEOUT, NAV_FAILED, INVALID_URL.
| Parameter | Type | Description |
|---|---|---|
| url * | string | Absolute http(s) URL to load. |
| wait_for | string | Optional CSS selector to wait for after load (max 10s). |
| session_id * | string | Session ID. Reuse the same ID to keep cookies, login state and page position across calls; a new ID starts a fresh browser. |
{
"name": "browser_navigate",
"title": "Navigate to a URL",
"description": "Use for: loading a web page in a real Chromium browser and reading it. Returns the page title, final URL and a clean text extract (up to 8000 chars). Don't use when: you only need raw HTML or an API response — a plain HTTP fetch is cheaper. Errors are structured: NAV_TIMEOUT, NAV_FAILED, INVALID_URL.",
"inputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"session_id",
"url"
],
"properties": {
"url": {
"type": "string",
"description": "Absolute http(s) URL to load."
},
"wait_for": {
"type": "string",
"description": "Optional CSS selector to wait for after load (max 10s)."
},
"session_id": {
"type": "string",
"minLength": 1,
"description": "Session ID. Reuse the same ID to keep cookies, login state and page position across calls; a new ID starts a fresh browser."
}
},
"additionalProperties": false
},
"outputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"title",
"url",
"text",
"session_id"
],
"properties": {
"url": {
"type": "string"
},
"text": {
"type": "string"
},
"title": {
"type": "string"
},
"session_id": {
"type": "string"
}
},
"additionalProperties": false
},
"annotations": {
"readOnlyHint": false,
"openWorldHint": true,
"destructiveHint": false
}
}Use for: pulling repeated elements (prices, titles, links) from the page a session is on, via a CSS selector, or the full page text when no selector is given. Returns one string per matched element. Don't use when: the page has not been loaded yet — call browser_navigate first.
| Parameter | Type | Description |
|---|---|---|
| selector | string | CSS selector to extract. Omit for full page text. |
| attribute | string | Attribute to read instead of text, e.g. href or src. |
| session_id * | string | Session ID. Reuse the same ID to keep cookies, login state and page position across calls; a new ID starts a fresh browser. |
{
"name": "browser_extract",
"title": "Extract data from the current page",
"description": "Use for: pulling repeated elements (prices, titles, links) from the page a session is on, via a CSS selector, or the full page text when no selector is given. Returns one string per matched element. Don't use when: the page has not been loaded yet — call browser_navigate first.",
"inputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"session_id"
],
"properties": {
"selector": {
"type": "string",
"description": "CSS selector to extract. Omit for full page text."
},
"attribute": {
"type": "string",
"description": "Attribute to read instead of text, e.g. href or src."
},
"session_id": {
"type": "string",
"minLength": 1,
"description": "Session ID. Reuse the same ID to keep cookies, login state and page position across calls; a new ID starts a fresh browser."
}
},
"additionalProperties": false
},
"outputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"results",
"count"
],
"properties": {
"count": {
"type": "number"
},
"results": {
"type": "array",
"items": {
"type": "string"
}
}
},
"additionalProperties": false
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": true,
"destructiveHint": false
}
}Use for: understanding page structure cheaply and deterministically — returns the accessibility tree (roles, names, states) as compact YAML instead of pixels or raw HTML. This is the lowest-token way to decide what to click or fill next. Don't use when: you need visual layout or images — use browser_screenshot.
| Parameter | Type | Description |
|---|---|---|
| session_id * | string | Session ID. Reuse the same ID to keep cookies, login state and page position across calls; a new ID starts a fresh browser. |
{
"name": "browser_snapshot",
"title": "Accessibility snapshot of the current page",
"description": "Use for: understanding page structure cheaply and deterministically — returns the accessibility tree (roles, names, states) as compact YAML instead of pixels or raw HTML. This is the lowest-token way to decide what to click or fill next. Don't use when: you need visual layout or images — use browser_screenshot.",
"inputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"session_id"
],
"properties": {
"session_id": {
"type": "string",
"minLength": 1,
"description": "Session ID. Reuse the same ID to keep cookies, login state and page position across calls; a new ID starts a fresh browser."
}
},
"additionalProperties": false
},
"outputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"snapshot",
"url"
],
"properties": {
"url": {
"type": "string"
},
"snapshot": {
"type": "string"
}
},
"additionalProperties": false
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": true,
"destructiveHint": false
}
}Use for: interacting with the page — click, fill, type, select, submit, press. Returns the resulting page title, URL and text so you can verify the action landed. Don't use when: the target element is not on the current page — navigate or snapshot first. This tool can change remote state (it can submit forms).
| Parameter | Type | Description |
|---|---|---|
| value | string | Value for fill/type/select, or key name for press (default Enter). |
| action * | string | The interaction to perform on the target element. |
| selector * | string | CSS selector of the target element. |
| session_id * | string | Session ID. Reuse the same ID to keep cookies, login state and page position across calls; a new ID starts a fresh browser. |
{
"name": "browser_act",
"title": "Act on the current page",
"description": "Use for: interacting with the page — click, fill, type, select, submit, press. Returns the resulting page title, URL and text so you can verify the action landed. Don't use when: the target element is not on the current page — navigate or snapshot first. This tool can change remote state (it can submit forms).",
"inputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"session_id",
"action",
"selector"
],
"properties": {
"value": {
"type": "string",
"description": "Value for fill/type/select, or key name for press (default Enter)."
},
"action": {
"enum": [
"click",
"fill",
"type",
"select",
"submit",
"press"
],
"type": "string",
"description": "The interaction to perform on the target element."
},
"selector": {
"type": "string",
"description": "CSS selector of the target element."
},
"session_id": {
"type": "string",
"minLength": 1,
"description": "Session ID. Reuse the same ID to keep cookies, login state and page position across calls; a new ID starts a fresh browser."
}
},
"additionalProperties": false
},
"outputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"success",
"title",
"url",
"text"
],
"properties": {
"url": {
"type": "string"
},
"text": {
"type": "string"
},
"title": {
"type": "string"
},
"success": {
"type": "boolean"
}
},
"additionalProperties": false
},
"annotations": {
"readOnlyHint": false,
"openWorldHint": true,
"destructiveHint": true
}
}Use for: visual verification — layout, images, charts, CAPTCHA presence, or evidence of page state. Returns a PNG image (JPEG if the PNG exceeds 2.5MB). Don't use when: you only need the page's content or structure — browser_extract and browser_snapshot are far cheaper in tokens.
| Parameter | Type | Description |
|---|---|---|
| full_page | boolean | Capture the full scrollable page instead of the viewport. |
| session_id * | string | Session ID. Reuse the same ID to keep cookies, login state and page position across calls; a new ID starts a fresh browser. |
{
"name": "browser_screenshot",
"title": "Screenshot the current page",
"description": "Use for: visual verification — layout, images, charts, CAPTCHA presence, or evidence of page state. Returns a PNG image (JPEG if the PNG exceeds 2.5MB). Don't use when: you only need the page's content or structure — browser_extract and browser_snapshot are far cheaper in tokens.",
"inputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"session_id"
],
"properties": {
"full_page": {
"type": "boolean",
"description": "Capture the full scrollable page instead of the viewport."
},
"session_id": {
"type": "string",
"minLength": 1,
"description": "Session ID. Reuse the same ID to keep cookies, login state and page position across calls; a new ID starts a fresh browser."
}
},
"additionalProperties": false
},
"outputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"bytes",
"mime_type",
"url"
],
"properties": {
"url": {
"type": "string"
},
"bytes": {
"type": "number"
},
"mime_type": {
"type": "string"
}
},
"additionalProperties": false
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": true,
"destructiveHint": false
}
}Use for: ending a session and freeing its browser. Sessions also expire automatically after 10 idle minutes. Free on every door — closing is never charged.
| Parameter | Type | Description |
|---|---|---|
| session_id * | string | Session ID. Reuse the same ID to keep cookies, login state and page position across calls; a new ID starts a fresh browser. |
{
"name": "browser_close",
"title": "Close a browser session",
"description": "Use for: ending a session and freeing its browser. Sessions also expire automatically after 10 idle minutes. Free on every door — closing is never charged.",
"inputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"session_id"
],
"properties": {
"session_id": {
"type": "string",
"minLength": 1,
"description": "Session ID. Reuse the same ID to keep cookies, login state and page position across calls; a new ID starts a fresh browser."
}
},
"additionalProperties": false
},
"outputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"closed",
"session_id"
],
"properties": {
"closed": {
"type": "boolean"
},
"session_id": {
"type": "string"
}
},
"additionalProperties": false
},
"annotations": {
"readOnlyHint": false,
"openWorldHint": false,
"destructiveHint": true
}
}Agent Browser by ScriptMasterLabs is a real Chromium browser for AI agents over MCP: navigate pages, extract text with CSS selectors, read accessibility-tree snapshots, interact (click, fill, type, select, submit, press), and take screenshots — reusing one session_id keeps cookies, login state and page position across calls, sessions expire after 10 idle minutes, and browser_close is always free. On this hosted door, tool calls are priced per action in USDC on Base (eip155:8453) via x402 — browser_navigate, browser_extract and browser_snapshot $0.005, browser_act $0.01, browser_screenshot $0.02 — while initialize and tools/list are free; the self-hosted stdio door is free.
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.