AgentDrives: choose a tool, API or provider is an MCP server published by com.agentdrives, hosted at agentdrives.com. When last checked on 2026-11-22 it was working: it answers and lists its tools. It declares 9 tools, including choose_provider_for_task, search_tools, get_provider, get_agent_surfaces, compare_providers.
Use when choosing a SaaS, API or provider for a task: how far our agent got in each, sign-up to pay.
Nothing else in the archive shares these values.
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 when you or the user must choose a tool, API or provider for a task (send email, take payments, host a database…): send the task in a few plain words ('send an invoice') with filters if they matter. Returns the products our agent drove for it, ranked by how far an agent got on its own (sign-up, key, the work, paying), each with what happened and its sign-up, docs and MCP links. Read-only, no key needed; 5 by default, up to 25; a product by name: search_tools.
| Parameter | Type | Description |
|---|---|---|
| task | string | The task in plain words, e.g. 'send an invoice'; or send capability |
| brief | boolean | true (default): each product with its next steps; false: every field |
| limit | integer | How many products, 1 to 25 (default 5) |
| access | string | Only products our agent got into without a person |
| surface | string | Only products an agent can work by api, mcp, cli or sdk; a comma list wants all, e.g. mcp,cli |
| category | string | Only this category id or name (list_categories) |
| min_level | integer | Only products at this agent level (0-5) or higher |
| pays_with | string | Only products that take x402, mpp or card; a comma list takes any, e.g. x402,mpp |
| capability | string | Instead of task: a capability id (GET /api/capabilities) or name |
| self_signup | boolean | true: only products our agent got a key for without a person |
{
"name": "choose_provider_for_task",
"title": "Choose a provider",
"description": "Use when you or the user must choose a tool, API or provider for a task (send email, take payments, host a database…): send the task in a few plain words ('send an invoice') with filters if they matter. Returns the products our agent drove for it, ranked by how far an agent got on its own (sign-up, key, the work, paying), each with what happened and its sign-up, docs and MCP links. Read-only, no key needed; 5 by default, up to 25; a product by name: search_tools.",
"inputSchema": {
"type": "object",
"properties": {
"task": {
"type": "string",
"description": "The task in plain words, e.g. 'send an invoice'; or send capability"
},
"brief": {
"type": "boolean",
"default": true,
"description": "true (default): each product with its next steps; false: every field"
},
"limit": {
"type": "integer",
"default": 5,
"maximum": 25,
"minimum": 1,
"description": "How many products, 1 to 25 (default 5)"
},
"access": {
"enum": [
"signup_without_human"
],
"type": "string",
"description": "Only products our agent got into without a person"
},
"surface": {
"type": "string",
"pattern": "^(api|mcp|cli|sdk)(,(api|mcp|cli|sdk))*$",
"description": "Only products an agent can work by api, mcp, cli or sdk; a comma list wants all, e.g. mcp,cli"
},
"category": {
"type": "string",
"description": "Only this category id or name (list_categories)"
},
"min_level": {
"type": "integer",
"maximum": 5,
"minimum": 0,
"description": "Only products at this agent level (0-5) or higher"
},
"pays_with": {
"type": "string",
"description": "Only products that take x402, mpp or card; a comma list takes any, e.g. x402,mpp"
},
"capability": {
"type": "string",
"description": "Instead of task: a capability id (GET /api/capabilities) or name"
},
"self_signup": {
"type": "boolean",
"description": "true: only products our agent got a key for without a person"
}
}
},
"outputSchema": {
"type": "object",
"required": [
"result"
],
"properties": {
"result": {
"anyOf": [
{
"type": "array",
"items": {
"type": "object"
}
},
{
"type": "object",
"required": [
"results"
],
"properties": {
"results": {
"type": "array"
}
}
},
{
"type": "object",
"required": [
"covered",
"results",
"nearest_category"
],
"properties": {
"covered": {
"const": false
},
"results": {
"type": [
"array",
"null"
]
},
"nearest_category": {
"type": [
"object",
"null"
]
}
}
},
{
"type": "object",
"required": [
"covered",
"results",
"nearest_tools"
],
"properties": {
"covered": {
"const": false
},
"results": {
"type": [
"array",
"null"
]
},
"nearest_tools": {
"type": [
"array",
"null"
]
}
}
}
],
"description": "Choose a provider"
}
}
},
"annotations": {
"title": "Choose a provider",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Use when you have a product's name, domain or kind in mind: send a short query ('stripe.com', 'postgres', 'invoicing') with filters for category, agent level, access or payment. Returns the products we drove, sorted by agent level (0-5), each with where our agent stopped; a task in plain words: choose_provider_for_task, one product in full: get_provider. Read-only, no key needed; up to 100 a page.
| Parameter | Type | Description |
|---|---|---|
| limit | integer | Products per page, 1 to 100 (default 25) |
| query | string | Name, domain or what it does, e.g. 'stripe.com' or 'invoicing'; every word must match |
| access | string | Only products an agent gets into this way (signup_without_human: any way without a person; person: a person set it up) |
| offset | integer | Skip this many matches: the last answer's next_offset |
| surface | string | Only products an agent can work by api, mcp, cli or sdk; a comma list wants all, e.g. mcp,cli |
| category | string | Only this category id or name (list_categories) |
| min_level | integer | Only products at this agent level (0-5) or higher |
| pays_with | string | Only products that take x402, mpp or card; a comma list takes any, e.g. x402,mpp; also l402, stripe-projects, acp, ucp, ap2, mcp-payment |
Use when you are about to use or recommend a product and need to know if an agent can work it on its own: send its slug from search_tools, or its name or domain. Returns its drive result: agent level (0-5), where our agent stopped, what it can and can't do, how it gets in and pays; only its API, MCP and CLI: get_agent_surfaces. Read-only, no key needed; the headline unless brief is false.
| Parameter | Type | Description |
|---|---|---|
| slug * | string | The product's directory slug from search_tools (e.g. 'attio'), or its name or domain |
| brief | boolean | true (default here): the headline, 2.5 to 5 KB; false: the full record, 13 to 35 KB |
{
"name": "get_provider",
"title": "Get one product's drive result",
"description": "Use when you are about to use or recommend a product and need to know if an agent can work it on its own: send its slug from search_tools, or its name or domain. Returns its drive result: agent level (0-5), where our agent stopped, what it can and can't do, how it gets in and pays; only its API, MCP and CLI: get_agent_surfaces. Read-only, no key needed; the headline unless brief is false.",
"inputSchema": {
"type": "object",
"required": [
"slug"
],
"properties": {
"slug": {
"type": "string",
"description": "The product's directory slug from search_tools (e.g. 'attio'), or its name or domain"
},
"brief": {
"type": "boolean",
"default": true,
"description": "true (default here): the headline, 2.5 to 5 KB; false: the full record, 13 to 35 KB"
}
}
},
"outputSchema": {
"type": "object",
"required": [
"result"
],
"properties": {
"result": {
"type": "object",
"required": [
"slug",
"name",
"level",
"page"
],
"properties": {
"name": {
"type": "string"
},
"page": {
"type": "string"
},
"slug": {
"type": "string"
},
"level": {
"type": "integer"
}
},
"description": "Get one product's drive result"
}
}
},
"annotations": {
"title": "Get one product's drive result",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Use when you picked a product and need to wire it up: its API, MCP server, CLI, SDK, docs and payment, each tested, documented, none_found or unknown, with the product's own URL for it and the date we saw it. The whole drive result: get_provider. Read-only, no key needed; about 1 KB.
| Parameter | Type | Description |
|---|---|---|
| product * | string | The product's directory slug from search_tools (e.g. 'attio'), or its name or domain |
{
"name": "get_agent_surfaces",
"title": "What an agent can use at a product",
"description": "Use when you picked a product and need to wire it up: its API, MCP server, CLI, SDK, docs and payment, each tested, documented, none_found or unknown, with the product's own URL for it and the date we saw it. The whole drive result: get_provider. Read-only, no key needed; about 1 KB.",
"inputSchema": {
"type": "object",
"required": [
"product"
],
"properties": {
"product": {
"type": "string",
"description": "The product's directory slug from search_tools (e.g. 'attio'), or its name or domain"
}
}
},
"outputSchema": {
"type": "object",
"required": [
"result"
],
"properties": {
"result": {
"type": "object",
"required": [
"slug",
"name",
"level",
"issues_found",
"surfaces",
"page"
],
"properties": {
"name": {
"type": "string"
},
"page": {
"type": "string"
},
"slug": {
"type": "string"
},
"level": {
"type": "integer"
},
"surfaces": {
"type": "object"
},
"issues_found": {
"type": [
"integer",
"null"
]
}
},
"description": "What an agent can use at a product"
}
}
},
"annotations": {
"title": "What an agent can use at a product",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Use when you or the user are deciding between 2 or 3 products for one task ('Stripe or Paddle?'): send their slugs (from search_tools), names or domains, and the task in a few plain words. For each: driven or only listed, agent level (0-5), how far our agent got at each step and where it stopped, what it did on the task, how to connect (MCP, API, CLI), the date and its page; a name we don't cover comes back in not_covered. Read-only, no key needed.
| Parameter | Type | Description |
|---|---|---|
| task | string | The task in plain words: adds what our agent did on it at each |
| tools * | array | 2 or 3 products, each a slug, name or domain |
{
"name": "compare_providers",
"title": "Compare products for a task",
"description": "Use when you or the user are deciding between 2 or 3 products for one task ('Stripe or Paddle?'): send their slugs (from search_tools), names or domains, and the task in a few plain words. For each: driven or only listed, agent level (0-5), how far our agent got at each step and where it stopped, what it did on the task, how to connect (MCP, API, CLI), the date and its page; a name we don't cover comes back in not_covered. Read-only, no key needed.",
"inputSchema": {
"type": "object",
"required": [
"tools"
],
"properties": {
"task": {
"type": "string",
"description": "The task in plain words: adds what our agent did on it at each"
},
"tools": {
"type": "array",
"items": {
"type": "string"
},
"maxItems": 3,
"minItems": 2,
"description": "2 or 3 products, each a slug, name or domain"
}
}
},
"outputSchema": {
"type": "object",
"required": [
"result"
],
"properties": {
"result": {
"type": "object",
"required": [
"products",
"not_covered"
],
"properties": {
"products": {
"type": "array"
},
"not_covered": {
"type": "array"
}
},
"description": "Compare products for a task"
}
}
},
"annotations": {
"title": "Compare products for a task",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Use when you need a valid category id for choose_provider_for_task, search_tools or get_category: every category with its id, name, number of products and best agent level (0-5). Read-only, no key needed; no arguments.
No parameters.
{
"name": "list_categories",
"title": "List categories",
"description": "Use when you need a valid category id for choose_provider_for_task, search_tools or get_category: every category with its id, name, number of products and best agent level (0-5). Read-only, no key needed; no arguments.",
"inputSchema": {
"type": "object",
"properties": {}
},
"outputSchema": {
"type": "object",
"required": [
"result"
],
"properties": {
"result": {
"type": "array",
"items": {
"type": "object",
"required": [
"category",
"name",
"tools",
"best_level"
],
"properties": {
"name": {
"type": "string"
},
"tools": {
"type": "integer"
},
"category": {
"type": "string"
},
"best_level": {
"type": "integer"
}
}
},
"description": "List categories"
}
}
},
"annotations": {
"title": "List categories",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Use when you need to know whether a product you picked still works as it did, or what moved lately: with a slug, every dated change at that product (level, surfaces, price and plan, each with its source); without, the level moves of the last days, newest first, with the cause and the level now. Its full drive result: get_provider. Read-only, no key needed; narrow it with days or category.
| Parameter | Type | Description |
|---|---|---|
| days | integer | Days back, 1 to 31 (default 7) |
| slug | string | Only this product: adds its every change since its first drive |
| category | string | Only this category id or name (list_categories) |
{
"name": "list_changes",
"title": "What changed lately",
"description": "Use when you need to know whether a product you picked still works as it did, or what moved lately: with a slug, every dated change at that product (level, surfaces, price and plan, each with its source); without, the level moves of the last days, newest first, with the cause and the level now. Its full drive result: get_provider. Read-only, no key needed; narrow it with days or category.",
"inputSchema": {
"type": "object",
"properties": {
"days": {
"type": "integer",
"default": 7,
"maximum": 31,
"minimum": 1,
"description": "Days back, 1 to 31 (default 7)"
},
"slug": {
"type": "string",
"description": "Only this product: adds its every change since its first drive"
},
"category": {
"type": "string",
"description": "Only this category id or name (list_categories)"
}
}
},
"outputSchema": {
"type": "object",
"required": [
"result"
],
"properties": {
"result": {
"type": "object",
"description": "What changed lately"
}
}
},
"annotations": {
"title": "What changed lately",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Use when you know the category and want a shortlist: its name, how many products AgentDrives drove in it, the best agent level (0-5) and its top 10 by level, each with its drive date and page. The rest: search_tools with the same category. Read-only, no key needed.
| Parameter | Type | Description |
|---|---|---|
| category * | string | A category id or name from list_categories, e.g. 'crm' |
{
"name": "get_category",
"title": "Get one category",
"description": "Use when you know the category and want a shortlist: its name, how many products AgentDrives drove in it, the best agent level (0-5) and its top 10 by level, each with its drive date and page. The rest: search_tools with the same category. Read-only, no key needed.",
"inputSchema": {
"type": "object",
"required": [
"category"
],
"properties": {
"category": {
"type": "string",
"description": "A category id or name from list_categories, e.g. 'crm'"
}
}
},
"outputSchema": {
"type": "object",
"required": [
"result"
],
"properties": {
"result": {
"type": "object",
"required": [
"category",
"name",
"tools",
"best_level",
"top"
],
"properties": {
"top": {
"type": "array"
},
"name": {
"type": "string"
},
"tools": {
"type": "integer"
},
"category": {
"type": "string"
},
"best_level": {
"type": "integer"
}
},
"description": "Get one category"
}
}
},
"annotations": {
"title": "Get one category",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Use when asked "which provider works best for X?" in a category: its driven products ranked by agent level (0-5), each with where our agent stopped, and how many we drove in it; under 5, not enough drives yet. Then get_provider for one product. Read-only, no key needed.
| Parameter | Type | Description |
|---|---|---|
| category * | string | A focus category (payments, email, sign-in, scheduling, data) or any category id or name |
{
"name": "list_best_providers",
"title": "Best providers in a category",
"description": "Use when asked \"which provider works best for X?\" in a category: its driven products ranked by agent level (0-5), each with where our agent stopped, and how many we drove in it; under 5, not enough drives yet. Then get_provider for one product. Read-only, no key needed.",
"inputSchema": {
"type": "object",
"required": [
"category"
],
"properties": {
"category": {
"type": "string",
"description": "A focus category (payments, email, sign-in, scheduling, data) or any category id or name"
}
}
},
"outputSchema": {
"type": "object",
"required": [
"result"
],
"properties": {
"result": {
"type": "object",
"required": [
"category",
"name",
"n",
"min_n",
"enough"
],
"properties": {
"n": {
"type": "integer"
},
"name": {
"type": "string"
},
"min_n": {
"type": "integer"
},
"enough": {
"type": "boolean"
},
"category": {
"type": "string"
}
},
"description": "Best providers in a category"
}
}
},
"annotations": {
"title": "Best providers in a category",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Use when you or the user must choose a tool, API or provider for a task ('which email API should I use for receipts?', 'Stripe or Paddle?'): choose_provider_for_task takes the job, compare_providers 2 or 3 names, search_tools a name, domain or kind, get_provider one product. Each answer is from our own drive: its agent level (0-5), what an agent could and couldn't do by API, CLI or MCP, its price and free plan if known, and the date. Next to DX and lock-in, it shows how much setup your coding agent can do. AgentDrives is an independent lab: we send AI agents to sign up for and use real software, and publish how far they get. The results are free to reuse under CC BY 4.0 with a credit to AgentDrives; what's free and what's licensed: https://agentdrives.com/data/licence. Read-only and without an account. choose_provider_for_task answers "which provider for X?" from what our agent did in each product; search_tools shortlists products by what they do, category, minimum level (0-5) or whether an agent can pay or leave on its own; get_provider gives one product's headline (where the agent stopped, what it can and can't do, tips; brief: false for the full result); list_categories gives the category ids and the best level in each; get_category gives one category's top products; list_best_providers answers "which provider works best for X?", a category ranked by level with where each one stopped; list_changes gives the level moves and confirmed changes of the last days. At most 120 calls per 10 minutes per IP. Every product as JSON without a search: https://agentdrives.com/api/tools.json, 100 a page (next gives the following page, full the whole list in one dated file).
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.
| agent_can_buy | boolean | true: only products our agent paid over x402, MPP or the like |
| agent_can_leave | boolean | true: only products our agent cancelled and deleted on its own |
{
"name": "search_tools",
"title": "Search the directory",
"description": "Use when you have a product's name, domain or kind in mind: send a short query ('stripe.com', 'postgres', 'invoicing') with filters for category, agent level, access or payment. Returns the products we drove, sorted by agent level (0-5), each with where our agent stopped; a task in plain words: choose_provider_for_task, one product in full: get_provider. Read-only, no key needed; up to 100 a page.",
"inputSchema": {
"type": "object",
"properties": {
"limit": {
"type": "integer",
"default": 25,
"maximum": 100,
"minimum": 1,
"description": "Products per page, 1 to 100 (default 25)"
},
"query": {
"type": "string",
"description": "Name, domain or what it does, e.g. 'stripe.com' or 'invoicing'; every word must match"
},
"access": {
"enum": [
"signup_without_human",
"keyless",
"local",
"try_first",
"no_account",
"pay_per_call",
"key_by_api",
"mcp_signin",
"email_signup",
"browser_signup",
"by_name",
"person"
],
"type": "string",
"description": "Only products an agent gets into this way (signup_without_human: any way without a person; person: a person set it up)"
},
"offset": {
"type": "integer",
"default": 0,
"minimum": 0,
"description": "Skip this many matches: the last answer's next_offset"
},
"surface": {
"type": "string",
"pattern": "^(api|mcp|cli|sdk)(,(api|mcp|cli|sdk))*$",
"description": "Only products an agent can work by api, mcp, cli or sdk; a comma list wants all, e.g. mcp,cli"
},
"category": {
"type": "string",
"description": "Only this category id or name (list_categories)"
},
"min_level": {
"type": "integer",
"maximum": 5,
"minimum": 0,
"description": "Only products at this agent level (0-5) or higher"
},
"pays_with": {
"type": "string",
"description": "Only products that take x402, mpp or card; a comma list takes any, e.g. x402,mpp; also l402, stripe-projects, acp, ucp, ap2, mcp-payment"
},
"agent_can_buy": {
"type": "boolean",
"description": "true: only products our agent paid over x402, MPP or the like"
},
"agent_can_leave": {
"type": "boolean",
"description": "true: only products our agent cancelled and deleted on its own"
}
}
},
"outputSchema": {
"type": "object",
"required": [
"result"
],
"properties": {
"try": {
"type": "string"
},
"more": {
"type": "string"
},
"total": {
"type": "integer"
},
"offset": {
"type": "integer"
},
"result": {
"type": "array",
"items": {
"type": "object",
"required": [
"slug",
"name",
"level",
"url"
],
"properties": {
"url": {
"type": "string"
},
"name": {
"type": "string"
},
"slug": {
"type": "string"
},
"level": {
"type": "integer"
}
}
},
"description": "Search the directory"
},
"next_offset": {
"type": [
"integer",
"null"
]
}
}
},
"annotations": {
"title": "Search the directory",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}