How do I connect an AI agent to Mammoth Docs?

Use the MCP streamable HTTP endpoint https://docs.mammoth.io/mcp.

Catalog › io.mammoth/docs

Is Mammoth Docs reliable?

Reliable (measured) Yes. Faceabot measured Mammoth Docs 25 times: 100% of checks succeeded, including the last 25 in a row (last check 2026-10-19 19:20 UTC). It also does the job: its real read-only task worked 25 of 25 times.

Last check: 2026-10-19 19:20 UTC · answered in 5948 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 and read the Mammoth Analytics docs. Tools: search_docs, get_doc, list_docs.

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

Connect your agent

{
  "mcpServers": {
    "docs": {
      "url": "https://docs.mammoth.io/mcp"
    }
  }
}

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

Does it actually do the job?

Does the job (tested) — Faceabot asked list_docs to do a small read-only task 25 time(s): 25 returned a real result, the last 25 in a row. Last result: ok in 2282 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 19:20 UTC	✅ ok	✅ done	5948 ms
2026-10-19 05:50 UTC	✅ ok	✅ done	6629 ms
2026-10-18 13:35 UTC	✅ ok	✅ done	6233 ms
2026-10-18 03:40 UTC	✅ ok	✅ done	7445 ms
2026-10-17 19:40 UTC	✅ ok	✅ done	5874 ms
2026-10-17 11:20 UTC	✅ ok	✅ done	5433 ms
2026-10-17 03:35 UTC	✅ ok	✅ done	7756 ms
2026-10-16 19:55 UTC	✅ ok	✅ done	6691 ms
2026-10-16 12:46 UTC	✅ ok	✅ done	9897 ms
2026-10-16 05:50 UTC	✅ ok	✅ done	6268 ms
2026-10-15 22:55 UTC	✅ ok	✅ done	7178 ms
2026-10-15 16:02 UTC	✅ ok	✅ done	8148 ms
2026-10-15 09:21 UTC	✅ ok	✅ done	4553 ms
2026-10-15 02:50 UTC	✅ ok	✅ done	3583 ms
2026-10-14 20:25 UTC	✅ ok	✅ done	7484 ms
2026-10-14 13:55 UTC	✅ ok	✅ done	5874 ms
2026-10-14 07:30 UTC	✅ ok	✅ done	4254 ms
2026-10-14 00:41 UTC	✅ ok	✅ done	9187 ms
2026-10-13 18:35 UTC	✅ ok	✅ done	8526 ms
2026-10-13 12:25 UTC	✅ ok	✅ done	10463 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

Mammoth Analytics Private (key required)

Explore, clean, transform and export your Mammoth Analytics data from an AI client.

MCP endpoint : https://mcp.mammoth.io/mcp · website · measurements and details

Find tools similar to Mammoth Docs →

Publisher of Mammoth Docs?

Show your measured reliability on your README or website:

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

Data in JSON: /api/catalog?id=io.mammoth/docs · 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