Skip to content

AgentTool MCP server

Which MCP servers are AgentTool'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 2026-10-26

← Back to AgentTool

Whose server it is
  • Registry namedev.agenttool/agenttoolverified in the MCP registry

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

When we asked itchecked 2026-10-26
  • Stateanswerschecked 2026-10-26
  • Tools5
  • Server calls itselfagenttool
  • Server version1.0.0
  • Protocol version2025-11-25

On 2026-10-26 the server answered initialize and tools/list without a sign-in. First answer in 278 ms.

Should an agent connect itSkip it
  • Its tools do none of the product's use cases we checked: save and retrieve agent memory in chosen storage; inspect and install bounded tools for an agent; coordinate tasks between agents with explicit messages.
  • Checked on 1 of the 7 days it takes to judge reliability.

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: 1, the first on 2026-10-26
  • INITE MCP scoreafter a weeka score needs 7 daily checks: 1 so far
  • What an agent can do with it0 of 3 use cases
  • Answeredmeasuring1 of the 7 daily checks it takes to print a share
  • Median first answer279 ms
  • Space in an agent's context≈ 365 tokensthe definitions of all its tools (5), which an agent carries on every turn
  • Tool definitionsA · 100 of 100
  • Typed results0 of 5 toolsdeclared outputSchema: results come typed, read once
  • Every tool passes all six checks.

What an agent can do with it

  • cannot · save and retrieve agent memory in chosen storage
  • cannot · inspect and install bounded tools for an agent
  • cannot · coordinate tasks between agents with explicit messages

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 offers5 tools · read 2026-10-26
  • canon.lookup

    Resolve a canon concept by URN. Returns the JSON-LD entry plus its bidirectional neighbors (citations in + citations out).

  • canon.by_type

    List every registered canon entry of a given @type (e.g. DoctrineDoc, Wall, RingCommitment, Pattern, Promise). The prose corpus is broader than this registry.

  • canon.list_types

    List the type vocabulary of the canon registry. Returns the distinct @types plus the count of concepts in each.

  • canon.summary

    Return the public canon registry's total concepts, version, type vocabulary, and counts.

  • wake.platform

    Return the public platform-self payload — agenttool's identity, repo, doctrine roots. The platform block of GET /public/self.

How to connect

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

{
  "mcpServers": {
    "agenttool": {
      "type": "http",
      "url": "https://api.agenttool.dev/v1/mcp"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http agenttool https://api.agenttool.dev/v1/mcp

Add to CursorAdd to VS Code

claude.ai, ChatGPT and other clients: add https://api.agenttool.dev/v1/mcp as a custom connector in the settings.

OpenAPI spec

184 paths, read 2026-10-26. 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.