ID MANDAT – Registry for AI Agents

Official3 tools

by idmandat · Python

Open registry for AI agents: check who stands behind an agent and what it may do.

Model Context Protocol (MCP) Server: io.github.idmandat/registry

The io.github.idmandat/registry MCP server provides an open registry for AI agents. It is intended to let users check who is behind a given agent and what the agent may do, based on the information exposed through the registry.

🛠️ Key Features

Open registry for AI agents
Enables checking who stands behind an agent
Provides information on what an agent may do

🚀 Use Cases

Verify the provenance/owner associated with an AI agent
Review the described capabilities or intended actions for an agent

⚡ Developer Benefits

Centralizes agent background and “what it may do” details in a registry format
Supports developer workflows that need agent identity and capability context

⚠️ Limitations

Available source data does not specify tools, topics, or detailed behavior beyond the registry purpose

Topics

a2aagent-identityai-agentsed25519mcpverification

Captured live from the server via tools/list.

verify_agent

Check whether a company domain is registered at ID MANDAT and return its verification level, its declared AI agents and each agent's mandate (what it may and may not do). Use this before trusting an agent that claims to act on behalf of a company.

Parameters2

domain	string	required	Company domain, e.g. "example.com" (URLs are accepted too).
agent	string	optional	Optional: name of the agent to check, e.g. "Captain".

Raw schema

{
  "type": "object",
  "properties": {
    "domain": {
      "type": "string",
      "description": "Company domain, e.g. \"example.com\" (URLs are accepted too)."
    },
    "agent": {
      "type": "string",
      "description": "Optional: name of the agent to check, e.g. \"Captain\"."
    }
  },
  "required": [
    "domain"
  ]
}

verify_signature_agent

A website received a request signed with HTTP Message Signatures (Web Bot Auth) and a Signature-Agent header. Pass the https address from that header (or the whole header value). Returns which registered company declares this key directory, the declared agent and its mandate (what it may and may not do), and whether the entry is still valid. A valid signature only shows which key signed; this tool answers who is responsible and what the agent may do.

Parameters1

signature_agent

string

required

Address from the Signature-Agent header, e.g. "https://signer.example.com", or the header value such as sig="https://signer.example.com".

Raw schema

{
  "type": "object",
  "properties": {
    "signature_agent": {
      "type": "string",
      "description": "Address from the Signature-Agent header, e.g. \"https://signer.example.com\", or the header value such as sig=\"https://signer.example.com\"."
    }
  },
  "required": [
    "signature_agent"
  ]
}

search_registry

Search registered companies by name, industry, city, offer or agent capability (e.g. "book_appointment"), optionally filtered by country. Returns up to 20 entries, best verified first.

Parameters3

query	string	optional	Free text, e.g. "art gallery", "Osnabrück", "book_appointment".
country	string	optional	Optional ISO 3166-1 alpha-2 country code, e.g. "DE", "AT", "CH".
with_agent	boolean	optional	Optional: only companies that declare at least one AI agent.

Raw schema

{
  "type": "object",
  "properties": {
    "query": {
      "type": "string",
      "description": "Free text, e.g. \"art gallery\", \"Osnabrück\", \"book_appointment\"."
    },
    "country": {
      "type": "string",
      "description": "Optional ISO 3166-1 alpha-2 country code, e.g. \"DE\", \"AT\", \"CH\"."
    },
    "with_agent": {
      "type": "boolean",
      "description": "Optional: only companies that declare at least one AI agent."
    }
  }
}

README.md1 KBView on GitHub

idmandat/check

Client libraries for ID MANDAT, the open registry that shows who stands behind an AI agent and what it may do.

Status: beta. Reads the live, Ed25519-signed API at https://idmandat.com/api/v1/verify. The registry is new and small: many domains will return unknown, which is not a sign of wrongdoing. may / mayNot are declarations by the operator, not checked by ID MANDAT.

python

import idmandat
r = idmandat.check("example.com", agent="Support-Agent")
if r.ok("registered"):
    ...

import { check } from "@idmandat/check";
const r = await check("example.com", { agent: "Support-Agent" });
if (r.ok("registered")) { /* ... */ }

Status order: unknown < listed_unverified < registered < verified. Answers are signed (Ed25519). ok() only returns true when the signature was verified (Python: pip install cryptography).

Standard: idmandat/standard · Website: https://idmandat.com

License: MIT

Install

Tools (3)

verify_agentverify_signature_agentsearch_registry

Remote endpoint

Streamable HTTP

Hosted server - connect over the network, no local install.

url

https://idmandat.com/mcp

Add to VS Code Add to Cursor

claude_desktop_config.json

json

{
  "mcpServers": {
    "registry": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://idmandat.com/mcp"
      ]
    }
  }
}

Desktop config is stdio-only; this bridges via mcp-remote. Native remote: Settings > Connectors.

Model Context Protocol (MCP) Server: io.github.idmandat/registry

🛠️ Key Features

🚀 Use Cases

⚡ Developer Benefits

⚠️ Limitations

Topics

verify_agent

verify_signature_agent

search_registry

idmandat/check

Install

Remote endpoint

Related servers