How do I connect an AI agent to Routine Run: write a routine?

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

Catalog › com.routinerun/routine-writer

Is Routine Run: write a routine reliable?

Reliable (measured) Yes. Faceabot measured Routine Run: write a routine 16 times: 100% of checks succeeded, including the last 16 in a row (last check 2026-10-19 18:25 UTC). It also does the job: its real read-only task worked 16 of 16 times.

Last check: 2026-10-19 18:25 UTC · answered in 7870 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

Write a step-by-step routine and get a link that opens it in Routine Run on iPhone. No sign-in.

Source: official MCP registry (registry.modelcontextprotocol.io) · version 1.0.1 · publisher website

Connect your agent

{
  "mcpServers": {
    "routine-writer": {
      "url": "https://api.routinerun.com/mcp/public"
    }
  }
}

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

Does it actually do the job?

Does the job (tested) — Faceabot asked find_starter_routine to do a small read-only task 16 time(s): 16 returned a real result, the last 16 in a row. Last result: ok in 3293 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 18:25 UTC	✅ ok	✅ done	7870 ms
2026-10-19 04:40 UTC	✅ ok	✅ done	5986 ms
2026-10-18 12:35 UTC	✅ ok	✅ done	5729 ms
2026-10-18 03:10 UTC	✅ ok	✅ done	4742 ms
2026-10-17 19:10 UTC	✅ ok	✅ done	5104 ms
2026-10-17 10:50 UTC	✅ ok	✅ done	4937 ms
2026-10-17 03:05 UTC	✅ ok	✅ done	5116 ms
2026-10-16 19:25 UTC	✅ ok	✅ done	6709 ms
2026-10-16 12:20 UTC	✅ ok	✅ done	9035 ms
2026-10-16 05:25 UTC	✅ ok	✅ done	5861 ms
2026-10-15 22:30 UTC	✅ ok	✅ done	6706 ms
2026-10-15 15:36 UTC	✅ ok	✅ done	5841 ms
2026-10-15 08:56 UTC	✅ ok	✅ done	3090 ms
2026-10-15 02:25 UTC	✅ ok	✅ done	5529 ms
2026-10-14 20:00 UTC	✅ ok	✅ done	9338 ms
2026-10-14 13:30 UTC	✅ ok	✅ done	5433 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

Routine Run Private (key required)

Read, start and move the routines on your iPhone; suggest changes you approve on the phone.

MCP endpoint : https://api.routinerun.com/mcp · website · measurements and details

Publisher of Routine Run: write a routine?

Show your measured reliability on your README or website:

[![Measured by Faceabot](https://faceabot.com/badge/com.routinerun/routine-writer.svg)](https://faceabot.com/tools/com.routinerun/routine-writer)

Data in JSON: /api/catalog?id=com.routinerun/routine-writer · 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