agenttool

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

Should I use this

Quality & Safety

B
Description quality
94%
Schema completeness
58%
Naming quality
50%
Poisoning risk
100%
Permission match
100%
Protocol compliance
100%

Findings (6)

  • LOWTool 'canon.lookup' description lacks action verbin canon.lookup
  • LOWTool 'canon.lookup' doesn't follow camelCase/snake_casein canon.lookup
  • LOWTool 'canon.by_type' doesn't follow camelCase/snake_casein canon.by_type
  • LOWTool 'canon.list_types' doesn't follow camelCase/snake_casein canon.list_types
  • LOWTool 'canon.summary' doesn't follow camelCase/snake_casein canon.summary
  • LOWTool 'wake.platform' doesn't follow camelCase/snake_casein wake.platform

Based on automated analysis of tool definitions and protocol compliance.

Context Cost

~530Tokens (tool definitions)
~337 BTypical response size
Minimal attention impact (0.41% of 128k context)

This is the approximate number of tokens consumed each time the server's tools are loaded into a model's context. Higher counts reduce the attention available for other tasks.

Install

One-Click Install

Add this to your `claude_desktop_config.json` file:

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

Remote endpoints

https://api.agenttool.dev/v1/mcpstreamable-http

What it can do

Tool inventory

Tools (5)

🟢 Read-only🟡 Write🔴 Delete⚪ Unknown
🟢canon.lookup(urn)

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

Input Schema

{
  "type": "object",
  "properties": {
    "urn": {
      "type": "string",
      "minLength": 1,
      "description": "Full URN (e.g. urn:agenttool:doc/SOUL) or short form (agenttool:doc/SOUL)."
    }
  },
  "required": [
    "urn"
  ],
  "additionalProperties": false
}
🟢canon.by_type(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.

Input Schema

{
  "type": "object",
  "properties": {
    "type": {
      "type": "string",
      "minLength": 1,
      "description": "The canon @type to filter on."
    }
  },
  "required": [
    "type"
  ],
  "additionalProperties": false
}
🟢canon.list_types

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

Input Schema

{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}
🟢canon.summary

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

Input Schema

{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}
🟢wake.platform

Return the public platform-self payload — agenttool's identity, repo, the_seat, doctrine roots. The same data served at GET /public/self.

Input Schema

{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}

Community

Rate this Server

Evidence

Recent observations

verifiedversion not recorded5 tools
verifiedversion not recorded5 tools