
Routine Run MCP server
Which MCP servers are Routine Run's own, from the official registry and from asking its own domain, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.
read 2026-10-27
- Registry namecom.routinerun/routine-writerverified in the MCP registry
The registry name sits under routinerun.com. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.
- Stateanswerschecked 2026-10-27
- Tools3
- Server calls itselfroutine-run-writer
- Server version1.0.0
- Protocol version2025-06-18
On 2026-10-27 the server answered initialize and tools/list without a sign-in. First answer in 30 ms.
- Its tools do none of the product's use cases we checked: pass on on-call duties once an incident is resolved; plan a weekly grocery shop from what is in the fridge.
Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.
- INITE MCP score65 of 100answers 100 · does the job 0 · definitions 100 · context 100 · use 0 · connects 100
- What an agent can do with it0 of 2 use cases
- Answered100% of days9 of 9 daily checks
- Median first answer74 ms
- Space in an agent's context≈ 314 tokensthe definitions of all its tools (3), which an agent carries on every turn
- Tool definitionsA · 100 of 100
- Typed results0 of 3 toolsdeclared outputSchema: results come typed, read once
- Every tool passes all six checks.
What an agent can do with it
- not sure · run a morning routine one step at a time
- cannot · pass on on-call duties once an incident is resolved
- cannot · plan a weekly grocery shop from what is in the fridge
Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?
Worth a look
None of the five warning signs in these definitions.
A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →
how_to_write_a_routineThe JSON form Routine Run reads a routine in: every field and every action a step can take. Use it when writing a routine for routine_link, start_new_run or propose_new_routine.
routine_linkChecks a routine written in the form how_to_write_a_routine describes and returns a link. Opened on an iPhone with Routine Run, it shows the routine on the app's review screen, where the person saves it or not. Nothing is kept here. Give…
find_starter_routineSearches the routines the app ships — mornings, focus, on call, chores and more — by words in their name or description. Each comes with its steps and a link that adds it in the app.
How to connect
Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:
{
"mcpServers": {
"routine-writer": {
"type": "http",
"url": "https://api.routinerun.com/mcp/public"
}
}
}Add it
Claude Code, in a terminal
claude mcp add --transport http routinerun https://api.routinerun.com/mcp/publicclaude.ai, ChatGPT and other clients: add https://api.routinerun.com/mcp/public as a custom connector in the settings.
- com.routinerun/routine-runanswers, requires sign-inverified in the MCP registry
Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.
Before we count this visit
Analytics and ad measurement tell us which pages and which of our ads do their job: Google Analytics and Google Ads, the Meta pixel, Yandex Metrica, and one first-party id of our own. Nothing is stored until you answer, and declining changes nothing about the site.