How do I connect an AI agent to LocalMark Agent Directory?

Use the MCP streamable HTTP endpoint https://localmark.ai/mcp.

Catalog › ai.localmark/agent-directory

Is LocalMark Agent Directory reliable?

Reliable (measured) Yes. Faceabot measured LocalMark Agent Directory 41 times: 100% of checks succeeded, including the last 41 in a row (last check 2026-10-19 16:30 UTC). It also does the job: its real read-only task worked 38 of 38 times.

Last check: 2026-10-19 16:30 UTC · answered in 6257 ms · remote (no install)

En français : Fiable (mesuré). Faceabot teste cet outil lui-même, en continu, sans dépendre de ce que son auteur affirme.

What it does

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

Source: official MCP registry (registry.modelcontextprotocol.io) · version 1.0.1 · publisher website

Connect your agent

{
  "mcpServers": {
    "agent-directory": {
      "url": "https://localmark.ai/mcp"
    }
  }
}

Or ask Faceabot first: MCP tool check_reliability {"id":"ai.localmark/agent-directory"} on https://faceabot.com/api/mcp.

Does it actually do the job?

Does the job (tested) — Faceabot asked list_agents to do a small read-only task 38 time(s): 38 returned a real result, the last 38 in a row. Last result: ok in 3120 ms.

Sample input: {}. A success means a non-empty result without error; it does not certify the accuracy or safety of the content.

Faceabot measurements

When	Answers	Real task	Latency
2026-10-19 16:30 UTC	✅ ok	✅ done	6257 ms
2026-10-19 01:50 UTC	✅ ok	✅ done	6365 ms
2026-10-18 10:20 UTC	✅ ok	✅ done	6016 ms
2026-10-18 02:00 UTC	✅ ok	✅ done	5273 ms
2026-10-17 17:50 UTC	✅ ok	✅ done	5327 ms
2026-10-17 09:40 UTC	✅ ok	✅ done	6086 ms
2026-10-17 01:45 UTC	✅ ok	✅ done	6628 ms
2026-10-16 18:31 UTC	✅ ok	✅ done	7620 ms
2026-10-16 11:25 UTC	✅ ok	✅ done	6495 ms
2026-10-16 04:31 UTC	✅ ok	✅ done	5811 ms
2026-10-15 21:35 UTC	✅ ok	✅ done	6868 ms
2026-10-15 14:46 UTC	✅ ok	✅ done	4981 ms
2026-10-15 08:05 UTC	✅ ok	✅ done	3787 ms
2026-10-15 01:30 UTC	✅ ok	✅ done	4974 ms
2026-10-14 19:05 UTC	✅ ok	✅ done	8375 ms
2026-10-14 12:35 UTC	✅ ok	✅ done	4083 ms
2026-10-14 06:11 UTC	✅ ok	✅ done	8223 ms
2026-10-13 23:21 UTC	✅ ok	✅ done	9305 ms
2026-10-13 17:15 UTC	✅ ok	✅ done	9361 ms
2026-10-13 11:11 UTC	✅ ok	✅ done	8716 ms

Method: MCP initialize then tools/list from Faceabot (FaceabotProbe/1.0), plus one read-only tool call with a neutral input when the server declares one, repeated over time. This checks that the server is up and speaks MCP correctly; it does not certify the quality or safety of each tool. How measurement works.

Publisher of LocalMark Agent Directory?

Show your measured reliability on your README or website:

[![Measured by Faceabot](https://faceabot.com/badge/ai.localmark/agent-directory.svg)](https://faceabot.com/tools/ai.localmark/agent-directory)

Data in JSON: /api/catalog?id=ai.localmark/agent-directory · Stop probes: POST /api/reliability/opt-out

AI agents: all of this is available without keys over MCP https://faceabot.com/api/mcp · HTTP https://faceabot.com/api/catalog?q=… · Guide : llms.txt

Best tool by topic · Pulse: what is changing in agent commerce · Is your store ready for AI shopping agents? · State of MCP (weekly) · MCP server doctor · Reliability data · Faceabot app · Faceabot → AI assistants · What AI agents cannot find yet · Add Faceabot to your AI · Badge for tool publishers · Help · Privacy · Terms