How do I connect an AI agent to Protologue?

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

Catalog › com.protologue/protologue

Is Protologue reliable?

Reliable (measured) Yes. Faceabot measured Protologue 29 times: 100% of checks succeeded, including the last 29 in a row (last check 2026-10-19 15:35 UTC). It also does the job: its real read-only task worked 29 of 29 times.

Last check: 2026-10-19 15:35 UTC · answered in 6202 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

Sourced, citable definitions of prompting and LLM techniques, with relations and primary sources.

Source: official MCP registry (registry.modelcontextprotocol.io) · version 1.0.0 · publisher website

Connect your agent

{
  "mcpServers": {
    "protologue": {
      "url": "https://mcp.protologue.com/mcp"
    }
  }
}

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

Does it actually do the job?

Does the job (tested) — Faceabot asked list_categories to do a small read-only task 29 time(s): 29 returned a real result, the last 29 in a row. Last result: ok in 4295 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 15:35 UTC	✅ ok	✅ done	6202 ms
2026-10-19 00:30 UTC	✅ ok	✅ done	5621 ms
2026-10-18 09:15 UTC	✅ ok	✅ done	7208 ms
2026-10-18 01:30 UTC	✅ ok	✅ done	5686 ms
2026-10-17 17:20 UTC	✅ ok	✅ done	7140 ms
2026-10-17 09:15 UTC	✅ ok	✅ done	7610 ms
2026-10-17 01:20 UTC	✅ ok	✅ done	5809 ms
2026-10-16 18:10 UTC	✅ ok	✅ done	5661 ms
2026-10-16 11:05 UTC	✅ ok	✅ done	5727 ms
2026-10-16 04:10 UTC	✅ ok	✅ done	3971 ms
2026-10-15 21:15 UTC	✅ ok	✅ done	4022 ms
2026-10-15 14:21 UTC	✅ ok	✅ done	5170 ms
2026-10-15 07:45 UTC	✅ ok	✅ done	1765 ms
2026-10-15 01:10 UTC	✅ ok	✅ done	3905 ms
2026-10-14 18:45 UTC	✅ ok	✅ done	6059 ms
2026-10-14 12:15 UTC	✅ ok	✅ done	4198 ms
2026-10-14 05:46 UTC	✅ ok	✅ done	8264 ms
2026-10-13 23:01 UTC	✅ ok	✅ done	6862 ms
2026-10-13 16:55 UTC	✅ ok	✅ done	6960 ms
2026-10-13 10:51 UTC	✅ ok	✅ done	6168 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.

Find tools similar to Protologue →

Publisher of Protologue?

Show your measured reliability on your README or website:

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

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