Darmousseh MCP server
Which MCP servers are Darmousseh'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 2026-11-08
- Registry namecom.darmousseh/watchverified in the MCP registry
The registry name sits under darmousseh.com. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.
- Staterequires sign-inchecked 2026-11-08
On 2026-11-08 the server answered and asked for a sign-in with a Darmousseh account (OAuth). It shows its tool list only to signed-in users, so we list none here.
Should an agent connect it
- Whether its tools do the product's job has not been judged yet.
Once connected
- create-watch, delete-watch change data without a sign-in: anyone with the address can call them.
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.
Measured daily
- INITE MCP score68 of 100answers 100 · definitions 81 · context 100 · connects 100 · lowered until one of our scenario runs passes · lowered by the warning signs below
- Answered100% of days14 of 14 daily checks
- Median first answer88 ms
- Space in an agent's context≈ 796 tokensthe definitions of all its tools (6), which an agent carries on every turn
- Tool definitionsB · 81 of 100
- Typed results0 of 6 toolsdeclared outputSchema: results come typed, read once
- Parameters without a description: in 1 of 6
- Not saying whether it only reads or can destroy: 6 of 6
Worth a look
- Tools that change data, on a server that answers without a sign-in: create-watch, delete-watch
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 →
pingCheck the key works and show its plan limits. Read-only; creates nothing.
create-watchStart watching a URL; checks it on a schedule and records changes. Does one check now to set the baseline; does not notify for the baseline. Give at most one of keyword or condition+threshold, and one of selector or json_path.
list-watchesList your watches, newest first, 10 per page. Read-only.
get-watchShow one watch with its last value, status and webhook secret. Read-only.
delete-watchStop and remove a watch. Its recorded changes stay readable. Cannot be undone.
list-changesList recorded changes. With no cursor returns the 10 newest; with since returns changes after that cursor, oldest first, for polling. Read-only.
How to connect
Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:
{
"mcpServers": {
"watch": {
"type": "http",
"url": "https://watch.darmousseh.com/mcp"
}
}
}Add it
Claude Code, in a terminal
claude mcp add --transport http darmousseh https://watch.darmousseh.com/mcpclaude.ai, ChatGPT and other clients: add https://watch.darmousseh.com/mcp as a custom connector in the settings.
The first time it connects, the client opens a Darmousseh sign-in.
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.