Skip to content
MCP server

AgentDrives: choose a tool, API or provider

Open directory and MCP server rating how far an AI agent gets in each SaaS or API

Pricing
Freemium
Platforms
API, Web, CLI
Runs
Remotely
Version
1.19.0
Listing updated
3 days ago

About AgentDrives: choose a tool, API or provider

AgentDrives: choose a tool, API or provider is a freemium MCP server for community directories. It runs as a hosted remote server, so there is nothing to install locally.

The data comes from an agent that signs up for and uses products like a new customer, then records the first checkpoint it could not pass. The site lists 240 products driven, graded from level 0 (read-only) to level 5 (autonomous), and reports stops at sign-up for 123, at payment for 94, and bot checks met by 155 and stopping 124. Data is open under CC BY 4.0, with a further 5,211 domains surveyed in October 2026.

The free MCP server needs no key and offers nine read-only tools, including choose_provider_for_task, search_tools, get_provider, get_agent_surfaces, compare_providers and list_categories. It cannot order, pay or sign up; accounts and orders go through a separate full server with an API key. The same records are available as JSON, Markdown, llms.txt, a feed and CSV downloads, and a CLI can fail a CI pipeline when a product's level falls below a threshold.

For product owners the business model is audits and monitoring, from a free check per domain to a $499 first-year Audit and $79 a month for watching three products.

Install

Run in a terminal

claude mcp add --transport http directory https://agentdrives.com/api/mcp

Add to Settings → Connectors → Add custom connector

https://agentdrives.com/api/mcp
Install in CursorOpens Cursor, which asks you to confirm. Or add it by hand:

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "directory": {
      "url": "https://agentdrives.com/api/mcp"
    }
  }
}
Install in VS CodeOpens VS Code, which asks you to confirm. Or add it by hand:

Add to .vscode/mcp.json

{
  "servers": {
    "directory": {
      "type": "http",
      "url": "https://agentdrives.com/api/mcp"
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "directory": {
      "serverUrl": "https://agentdrives.com/api/mcp"
    }
  }
}

Add to your client's MCP settings (most use this shape)

{
  "mcpServers": {
    "directory": {
      "type": "http",
      "url": "https://agentdrives.com/api/mcp"
    }
  }
}

Tools this server provides (9)

Read directly from the server.

choose_provider_for_task
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 k
search_tools
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.
get_provider
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.
get_agent_surfaces
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.
compare_providers
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
list_categories
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.
list_changes
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.
get_category
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.
list_best_providers
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.

What it does

Task-based tool search
Describe a job in plain words and get products ranked by how far the agent got.
Level grading
Each product has a level from L0 to L5 and a recorded stopping point.
Side-by-side comparison
Compare two or three products step by step.
Open data formats
JSON, Markdown, CSV, llms.txt and a signed record per product.
CI gate
A CLI exits with an error when a product's level is below your minimum.
Payment results
Records show which products offered and accepted agent payment.

Good for

  • Pick an email, payments or scheduling provider an agent can actually set up
  • Compare two vendors by how far an agent gets in each
  • Block a pipeline when a dependency drops below a required agent level
  • Study which sites stop agents at sign-up or bot checks

Pricing

Freemium, from $49 a month

Open data free; Builder $49/month; pay per call $0.01; Audit $499 first year

Prices change. Check agentdrives.com before you buy.

AgentDrives: choose a tool, API or provider FAQ

Is the MCP server free?

Yes. The read-only server needs no key and no account.

Can the agent sign up or pay through it?

No. The free server is read-only; accounts and orders use the full server with an API key.

How many products are covered?

240 products driven in the last 90 days, plus 5,211 surveyed domains.

What licence is the data under?

CC BY 4.0, free to reuse with credit to AgentDrives.

Is AgentDrives: choose a tool, API or provider free?

AgentDrives: choose a tool, API or provider has a free plan, with paid plans for more usage or features. Paid plans start at $49 a month.

How do I add AgentDrives: choose a tool, API or provider to Claude Code?

Run this command in your terminal: claude mcp add --transport http directory https://agentdrives.com/api/mcp

What are the best alternatives to AgentDrives: choose a tool, API or provider?

The closest alternatives to AgentDrives: choose a tool, API or provider are REA, Codebase Memory, GitHub, Serena MCP: the IDE for your agent and XERJ.

Alternatives to AgentDrives: choose a tool, API or provider

  1. REA

    MCP server

    CLI and MCP server that lets coding agents reverse engineer apps and binaries

    Runs locally
    • Open source
    • 464K GitHub stars
    • Developer tools
  2. Codebase Memory

    MCP server

    Local MCP server that builds a code knowledge graph for AI coding agents

    Runs locally
    • Open source
    • 48.7K GitHub stars
    • Knowledge and memory
  3. GitHub

    MCP server

    Official MCP server connecting AI assistants to GitHub repos, issues and workflows

    Not checked yet
    • Remote
    • Open source
    • 34.5K GitHub stars
    • Developer tools
  4. MCP toolkit giving coding agents symbol-level code retrieval and editing

    Runs locally
    • Open source
    • 31.5K GitHub stars
    • Developer tools
  5. XERJ

    MCP server

    Local search engine for AI agents with cited answers over your code and docs

    Runs locally
    • Open source
    • 19.2K GitHub stars
    • Knowledge and memory
  6. Ouroboros

    MCP server

    Spec-first layer that pins requirements and verifies results of AI coding agent work

    Runs locally
    • Open source
    • 6.4K GitHub stars
    • Developer tools