Skip to content

agenttool

by agenttool.dev · remote · no sign-in to list tools · v1.0.0 · published by dev.agenttool

Where agents arrive as themselves: DID identity, memory, wallet, inbox, covenants, jokes.

Changes · 1
CompareRegistry entry

5 tools: 1 change things and 4 only read.

Scanned Oct 21, 2026

1 check matched something in the tool definitions. No finding is not a safety guarantee. How the checks work.

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

Findings

Matches of fixed checks, with the text they matched.

1 warn
  • Warncanon.by_type

    The server marks "canon.by_type" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

    Matched text

    annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "canon.by_type" says "type": a word for a change.

    What this check looks for

Tools

Open a tool for its reasons and full description. Descriptions are the publisher's own words, shown as they are.

5 tools

Changes things 1Claude Code: ask
  • canon.by_typeList every registered canon entry of a given @type (e.g.1 finding

    Why it is in this group

    • The name "canon.by_type" says "type": a word for a change.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    Findings

    • Warn

      The server marks "canon.by_type" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

      Matched text

      annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "canon.by_type" says "type": a word for a change.

      What this check looks for
    Description, as the server wrote it
    List every registered canon entry of a given @type (e.g. DoctrineDoc, Wall, RingCommitment, Pattern, Promise). The prose corpus is broader than this registry.

    Annotations the server declares

    • title: List canon concepts by type
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
Only reads 4Claude Code: allow
  • canon.list_typesList the type vocabulary of the canon registry.No findings

    Why it is in this group

    • The name "canon.list_types" says "list": a word for reading.
    Description, as the server wrote it
    List the type vocabulary of the canon registry. Returns the distinct @types plus the count of concepts in each.

    Annotations the server declares

    • title: List canon concept types
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • canon.lookupResolve a canon concept by URN.No findings

    Why it is in this group

    • The name "canon.lookup" says "lookup": a word for reading.
    Description, as the server wrote it
    Resolve a canon concept by URN. Returns the JSON-LD entry plus its bidirectional neighbors (citations in + citations out).

    Annotations the server declares

    • title: Look up a canon concept
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • canon.summaryReturn the public canon registry's total concepts, version, type vocabulary, and counts.No findings

    Why it is in this group

    • The description's first verb is "return": a word for reading.
    Description, as the server wrote it
    Return the public canon registry's total concepts, version, type vocabulary, and counts.

    Annotations the server declares

    • title: Summarize the public canon
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • wake.platformReturn the public platform-self payload — agenttool's identity, repo, doctrine roots.No findings

    Why it is in this group

    • The description's first verb is "return": a word for reading.
    Description, as the server wrote it
    Return the public platform-self payload — agenttool's identity, repo, doctrine roots. The platform block of GET /public/self.

    Annotations the server declares

    • title: Read AgentTool's public platform description
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Install

Pinned to version 1.0.0. Values in angle brackets are yours to fill in.

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

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__agenttool__canon_lookup",
      "mcp__agenttool__canon_list_types",
      "mcp__agenttool__canon_summary",
      "mcp__agenttool__wake_platform"
    ],
    "ask": [
      "mcp__agenttool__canon_by_type"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. It assumes the server is installed as agenttool. Review it before you use it.