Skip to content

io.github.jdhart81/agent-identity-registry

by jdhart81 · remote · no sign-in to list tools · v0.1.1 · published by GitHub user jdhart81

Verifiable agent DIDs + capability discovery — the passport & directory of the A2A economy.

Deletes · 1Changes · 1

6 tools: 1 can delete or cancel things, 1 change things and 4 only read.

Scanned Oct 21, 2026

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

claude mcp add --transport http agent-identity-registry https://mcp.viridisconservation.com/identity/mcp

Tools

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

6 tools

Deletes or cancels 1Claude Code: deny
  • revoke_agentRevoke an identity: it disappears from discovery (terminal) but its record is retained for auditability.No findings

    Why it is in this group

    • The name "revoke_agent" says "revoke": a word for removing or ending something.
    Description, as the server wrote it
    Revoke an identity: it disappears from discovery (terminal) but its record is retained for auditability.
Changes things 1Claude Code: ask
  • register_agentRegister (or idempotently update) an agent identity.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Register (or idempotently update) an agent identity. Returns a deterministic content-addressed DID. capabilities is a non-empty list of lowercase capability tags other agents can discover you by.
Only reads 4Claude Code: allow
  • describe_agentFleet-standard self-description.No findings

    Why it is in this group

    • The name "describe_agent" says "describe": a word for reading.
    Description, as the server wrote it
    Fleet-standard self-description.
  • discover_agentsFind ACTIVE agents matching ALL requested capabilities (AND semantics), deterministically ordered by match count then reputation.No findings

    Why it is in this group

    • The description's first verb is "find": a word for reading.
    Description, as the server wrote it
    Find ACTIVE agents matching ALL requested capabilities (AND semantics), deterministically ordered by match count then reputation.
  • list_registrationsList registrations, optionally filtered by status (ACTIVE|REVOKED).No findings

    Why it is in this group

    • The name "list_registrations" says "list": a word for reading.
    Description, as the server wrote it
    List registrations, optionally filtered by status (ACTIVE|REVOKED).
  • resolve_agentResolve an identity by agent_id or DID to its full public registration.No findings

    Why it is in this group

    • The name "resolve_agent" says "resolve": a word for reading.
    Description, as the server wrote it
    Resolve an identity by agent_id or DID to its full public registration.

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 0.1.1. Values in angle brackets are yours to fill in.

claude mcp add --transport http agent-identity-registry https://mcp.viridisconservation.com/identity/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__agent-identity-registry__resolve_agent",
      "mcp__agent-identity-registry__discover_agents",
      "mcp__agent-identity-registry__list_registrations",
      "mcp__agent-identity-registry__describe_agent"
    ],
    "ask": [
      "mcp__agent-identity-registry__register_agent"
    ],
    "deny": [
      "mcp__agent-identity-registry__revoke_agent"
    ]
  }
}

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 agent-identity-registry. Review it before you use it.