How do I connect an AI agent to Callejear Madrid?

Use the MCP streamable HTTP endpoint https://callejear.com/api/mcp.

Catalog › com.callejear/madrid

Is Callejear Madrid reliable?

Reliable (measured) Yes. Faceabot measured Callejear Madrid 17 times: 100% of checks succeeded, including the last 17 in a row (last check 2026-10-19 16:01 UTC). It also does the job: its real read-only task worked 17 of 17 times.

Last check: 2026-10-19 16:01 UTC · answered in 9101 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

Catálogo oficial de 9.400 vías de Madrid y métricas parciales de servicios a 500 m.

Source: official MCP registry (registry.modelcontextprotocol.io) · version 0.2.0 · publisher website

Connect your agent

{
  "mcpServers": {
    "madrid": {
      "url": "https://callejear.com/api/mcp"
    }
  }
}

Or ask Faceabot first: MCP tool check_reliability {"id":"com.callejear/madrid"} on https://faceabot.com/api/mcp.

Does it actually do the job?

Does the job (tested) — Faceabot asked callejear_get_coverage to do a small read-only task 17 time(s): 17 returned a real result, the last 17 in a row. Last result: ok in 2972 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 16:01 UTC	✅ ok	✅ done	9101 ms
2026-10-19 01:10 UTC	✅ ok	✅ done	6606 ms
2026-10-18 09:50 UTC	✅ ok	✅ done	7852 ms
2026-10-18 01:45 UTC	✅ ok	✅ done	6559 ms
2026-10-17 17:40 UTC	✅ ok	✅ done	5466 ms
2026-10-17 09:30 UTC	✅ ok	✅ done	7695 ms
2026-10-17 01:35 UTC	✅ ok	✅ done	4691 ms
2026-10-16 18:20 UTC	✅ ok	✅ done	6531 ms
2026-10-16 11:15 UTC	✅ ok	✅ done	6005 ms
2026-10-16 04:20 UTC	✅ ok	✅ done	4659 ms
2026-10-15 21:25 UTC	✅ ok	✅ done	6146 ms
2026-10-15 14:36 UTC	✅ ok	✅ done	4232 ms
2026-10-15 07:55 UTC	✅ ok	✅ done	3254 ms
2026-10-15 01:20 UTC	✅ ok	✅ done	3402 ms
2026-10-14 18:55 UTC	✅ ok	✅ done	5835 ms
2026-10-14 12:25 UTC	✅ ok	✅ done	4674 ms
2026-10-14 06:01 UTC	✅ ok	✅ done	9581 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.

More from the same publisher

Callejear France Reliable (measured) · 100% over 8 checks Does the job (tested) · 8/8

Search 2.19M French street records, IRIS-level amenities and commune-level risk codes.

MCP endpoint : https://callejear.fr/api/mcp · website · measurements and details

Publisher of Callejear Madrid?

Show your measured reliability on your README or website:

[![Measured by Faceabot](https://faceabot.com/badge/com.callejear/madrid.svg)](https://faceabot.com/tools/com.callejear/madrid)

Data in JSON: /api/catalog?id=com.callejear/madrid · 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