Skip to content
AgentDrives logo

AgentDrives MCP server

Which MCP servers are AgentDrives's own, from the official registry and from asking its own domain, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.

read 2026-10-28

← Back to AgentDrives

Whose server it is
  • Registry namecom.agentdrives/directoryverified in the MCP registry

The registry name sits under agentdrives.com. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.

When we asked itchecked 2026-10-28
  • Stateanswerschecked 2026-10-28
  • Tools6
  • Server calls itselfagentdrives-directory-public
  • Server version1.10.1
  • Protocol version2025-06-18

On 2026-10-28 the server answered initialize and tools/list without a sign-in. First answer in 521 ms.

Should an agent connect itNot proven either way yet
  • Its tools do every use case we checked: compare tools an agent can sign up for; check a product's docs for agent access.
  • Checked on 5 of the 7 days it takes to judge reliability.

Once connected

  • For "compare tools an agent can sign up for", the likely first call is find_tools_for_task.
  • For "check a product's docs for agent access", the likely first call is get_agent_surfaces.

Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.

Measured dailydaily checks: 5, the first on 2026-10-28
  • INITE MCP scoreafter a weeka score needs 7 daily checks: 5 so far
  • What an agent can do with it2 of 2 use cases
  • Answeredmeasuring5 of the 7 daily checks it takes to print a share
  • Median first answer521 ms
  • Space in an agent's context≈ 2,288 tokensthe definitions of all its tools (8), which an agent carries on every turn
  • Tool definitionsA · 100 of 100
  • Typed results8 of 8 toolsdeclared outputSchema: results come typed, read once
  • Every tool passes all six checks.

What an agent can do with it

  • not sure · find where an agent stops during signup
  • can do · compare tools an agent can sign up for
  • can do · check a product's docs for agent access

Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?

Worth a look

None of the five warning signs in these definitions.

A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →

Tools it offers6 tools · read 2026-10-28
  • find_tools_for_task

    Ranks the products AgentDrives has test-driven for a task given in plain words (e.g. 'send an invoice'). Each result: the agent level (0-5: 0 Read-only, 1 Needs a person, 2 Gets in, 3 Does the work, 4 Runs on its own, 5 Autonomous)…

  • search_tools

    Searches AgentDrives' tested products by name, domain or what they do. Filters: category, minimum agent level (0-5: 0 Read-only, 1 Needs a person, 2 Gets in, 3 Does the work, 4 Runs on its own, 5 Autonomous), how an agent gets in (access…

  • get_tool

    Returns any product we drove: its full test-drive result (13 to 35 KB, usually about 19 KB; brief: true gives the headline in 2.5 to 5 KB, usually about 3 KB): how far an agent gets with it and where it stops. slug: its directory slug…

  • list_categories

    Lists every category in the directory: its id (for search_tools' category filter), its name, the number of products listed in it and the best agent level in it (0-5).

  • what_changed

    What changed in the directory in the last days (default 7, at most 31): level_moves, each product's level going up or down between two of its drives, with the date, the cause in words (our agent changed, not confirmed by a second drive…

  • get_category

    One category of the directory: its name, how many products AgentDrives drove in it, the best agent level in it (0-5: 0 Read-only, 1 Needs a person, 2 Gets in, 3 Does the work, 4 Runs on its own, 5 Autonomous), and its top 10 products by…

How to connect

Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:

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

Add it

Claude Code, in a terminal

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

Add to CursorAdd to VS Code

claude.ai, ChatGPT and other clients: add https://agentdrives.com/api/mcp as a custom connector in the settings.

OpenAPI spec

88 paths, read 2026-10-28. Open the spec ↗

Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.