How do I connect an AI agent to Upfit Plan Builder?

Use the MCP streamable HTTP endpoint https://www.upfit.mobile/mcp.

Catalog › mobile.upfit/upfit

Is Upfit Plan Builder reliable?

Reliable (measured) Yes. Faceabot measured Upfit Plan Builder 15 times: 100% of checks succeeded, including the last 15 in a row (last check 2026-10-19 10:20 UTC). It also does the job: its real read-only task worked 15 of 15 times.

Last check: 2026-10-19 10:20 UTC · answered in 7183 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

Read-only bodyweight workout builder and exercise form cues from the Upfit iPhone app.

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

Connect your agent

{
  "mcpServers": {
    "upfit": {
      "url": "https://www.upfit.mobile/mcp"
    }
  }
}

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

Does it actually do the job?

Does the job (tested) — Faceabot asked list_exercises to do a small read-only task 15 time(s): 15 returned a real result, the last 15 in a row. Last result: ok in 1997 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 10:20 UTC	✅ ok	✅ done	7183 ms
2026-10-18 17:30 UTC	✅ ok	✅ done	8126 ms
2026-10-18 05:45 UTC	✅ ok	✅ done	7147 ms
2026-10-17 21:50 UTC	✅ ok	✅ done	6386 ms
2026-10-17 13:15 UTC	✅ ok	✅ done	7673 ms
2026-10-17 05:35 UTC	✅ ok	✅ done	6755 ms
2026-10-16 21:50 UTC	✅ ok	✅ done	5422 ms
2026-10-16 14:40 UTC	✅ ok	✅ done	7421 ms
2026-10-16 07:40 UTC	✅ ok	✅ done	8080 ms
2026-10-16 00:46 UTC	✅ ok	✅ done	8891 ms
2026-10-15 17:51 UTC	✅ ok	✅ done	7753 ms
2026-10-15 11:06 UTC	✅ ok	✅ done	5210 ms
2026-10-15 04:30 UTC	✅ ok	✅ done	3873 ms
2026-10-14 22:00 UTC	✅ ok	✅ done	9109 ms
2026-10-14 15:30 UTC	✅ ok	✅ done	7830 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 Upfit Plan Builder?

Show your measured reliability on your README or website:

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

Data in JSON: /api/catalog?id=mobile.upfit/upfit · 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