How do I connect an AI agent to Makuri Showcase (CogniLedger)?

Use the MCP streamable HTTP endpoint https://mcp.cogniledger.eu/mcp.

Catalog › io.github.Cogniledger/cogniledger-mcp-makuri

Is Makuri Showcase (CogniLedger) reliable?

Reliable (measured) Yes. Faceabot measured Makuri Showcase (CogniLedger) 42 times: 100% of checks succeeded, including the last 42 in a row (last check 2026-10-19 21:30 UTC).

Last check: 2026-10-19 21:30 UTC · answered in 6088 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

Makuri (EU AI tutoring for immigrant children): 11 tools, 2 interactive panels, no user data.

Source: official MCP registry (registry.modelcontextprotocol.io) · version 1.2.1 · publisher website

Connect your agent

{
  "mcpServers": {
    "cogniledger-mcp-makuri": {
      "url": "https://mcp.cogniledger.eu/mcp"
    }
  }
}

Or ask Faceabot first: MCP tool check_reliability {"id":"io.github.Cogniledger/cogniledger-mcp-makuri"} on https://faceabot.com/api/mcp.

Does it actually do the job?

Not tested with a real task yet. Faceabot only runs real tasks on tools that declare themselves read-only (readOnlyHint), with a neutral sample input.

Faceabot measurements

When	Answers	Real task	Latency
2026-10-19 21:30 UTC	✅ ok	—	6088 ms
2026-10-19 08:55 UTC	✅ ok	—	8597 ms
2026-10-18 16:05 UTC	✅ ok	—	7147 ms
2026-10-18 05:05 UTC	✅ ok	—	7660 ms
2026-10-17 21:10 UTC	✅ ok	—	6909 ms
2026-10-17 12:40 UTC	✅ ok	—	7626 ms
2026-10-17 05:00 UTC	✅ ok	—	8144 ms
2026-10-16 21:20 UTC	✅ ok	—	6233 ms
2026-10-16 14:15 UTC	✅ ok	—	8475 ms
2026-10-16 07:20 UTC	✅ ok	—	7018 ms
2026-10-16 00:30 UTC	✅ ok	—	5199 ms
2026-10-15 17:36 UTC	✅ ok	—	7151 ms
2026-10-15 10:50 UTC	✅ ok	—	3560 ms
2026-10-15 04:20 UTC	✅ ok	—	4150 ms
2026-10-14 21:55 UTC	✅ ok	—	5005 ms
2026-10-14 15:25 UTC	✅ ok	—	5807 ms
2026-10-14 09:01 UTC	✅ ok	—	2946 ms
2026-10-14 02:16 UTC	✅ ok	—	6270 ms
2026-10-13 20:05 UTC	✅ ok	—	8347 ms
2026-10-13 14:01 UTC	✅ ok	—	6603 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 Makuri Showcase (CogniLedger)?

Show your measured reliability on your README or website:

[![Measured by Faceabot](https://faceabot.com/badge/io.github.Cogniledger/cogniledger-mcp-makuri.svg)](https://faceabot.com/tools/io.github.Cogniledger/cogniledger-mcp-makuri)

Data in JSON: /api/catalog?id=io.github.Cogniledger/cogniledger-mcp-makuri · 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