Skip to content

LocalMark Agent Directory

by localmark.ai · remote · no sign-in to list tools · v1.0.1 · published by ai.localmark

Search public A2A agents and inspect read-only Agent Card and endpoint checks.

Changes · 1
CompareRegistry entry

6 tools: 1 change things and 5 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 agent-directory https://localmark.ai/mcp

Findings

Matches of fixed checks, with the text they matched.

1 info

Tools

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

6 tools

Changes things 1Claude Code: ask
  • recommend_agentsRecommend agents for a capability or job with matching reasons and caveats.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.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    Recommend agents for a capability or job with matching reasons and caveats. Uses exactly the website/API ranking and stored observations, never a live task. Filters are requirements, so an empty shortlist is valid. auth is 'none' or 'declared'; signature is 'verified'; protocol is JSONRPC, HTTP+JSON or GRPC. Observation age is 1..168 hours. max_amount is a non-negative amount in human-readable asset units (0.05 means 0.05 USDC for a USDC asset) and requires both network and asset with known decimals. No price conversion across assets is performed. Returns full structured results, total_matches, pagination, ranking_version and evidence scope.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: true
    • readOnlyHint: true
Only reads 5Claude Code: allow
  • get_agentGet one published agent's source, declared skills, and latest card check by LocalMark ID.No findings

    Why it is in this group

    • The name "get_agent" says "get": a word for reading.
    Description, as the server wrote it
    Get one published agent's source, declared skills, and latest card check by LocalMark ID.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: true
    • readOnlyHint: true
  • get_connection_planRead connection metadata for a public agent without connecting to it.1 finding

    Why it is in this group

    • The name "get_connection_plan" says "get": a word for reading.

    Findings

    • Info

      The description mentions "credentials".

      Matched text

      description: "...ambiguous. The plan never includes credentials and never authorizes a task or paym..."

      What this check looks for
    Description, as the server wrote it
    Read connection metadata for a public agent without connecting to it. Accepts a LocalMark agent ID, Agent Card URL, endpoint URL or domain. Returns advertised interfaces, authentication scheme metadata, input/output modes, skill names and stored evidence. A publisher domain may be ambiguous. The plan never includes credentials and never authorizes a task or payment. Obtain explicit task authorization before using any endpoint.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: true
    • readOnlyHint: true
  • list_agentsBrowse public agents with pagination.No findings

    Why it is in this group

    • The name "list_agents" says "list": a word for reading.
    Description, as the server wrote it
    Browse public agents with pagination.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: true
    • readOnlyHint: true
  • search_agentsSearch public agent names, descriptions, and declared skills.No findings

    Why it is in this group

    • The name "search_agents" says "search": a word for reading.
    Description, as the server wrote it
    Search public agent names, descriptions, and declared skills. Returns card and profile URLs, not task results.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: true
    • readOnlyHint: true
  • verify_agentRead stored checks for a card URL, endpoint URL or publisher domain.No findings

    Why it is in this group

    • The description's first verb is "read": a word for reading.
    Description, as the server wrote it
    Read stored checks for a card URL, endpoint URL or publisher domain. Unseen targets return listing_status 'not_seen', including available lookalike-domain hints. Publisher domains may return multiple matches. No live request is made to the publisher.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: true
    • readOnlyHint: true

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

claude mcp add --transport http agent-directory https://localmark.ai/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-directory__search_agents",
      "mcp__agent-directory__get_connection_plan",
      "mcp__agent-directory__list_agents",
      "mcp__agent-directory__get_agent",
      "mcp__agent-directory__verify_agent"
    ],
    "ask": [
      "mcp__agent-directory__recommend_agents"
    ],
    "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 agent-directory. Review it before you use it.