
Commet MCP server
Which MCP servers are Commet'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 2026-10-10
- Addresshttps://commet.co/mcpnot in the official registry: answered when asked
No entry in the official MCP registry names this server. It answered on commet.co when the Atlas asked at the address servers are usually mounted on, so it is the vendor's own. Clients and catalogues that list servers from the registry do not show it.
- Stateanswerschecked 2026-10-27
- Tools1
- Server calls itselfcommet
- 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 131 ms.
- Its tools do none of the product's use cases we checked: measure usage and manage subscriptions across payment providers; build and update pricing models without code changes; recover failed payments with smart retries and dunning.
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 score72 of 100answers 100 · does the job 0 · definitions 100 · context 100 · connects 100
- What an agent can do with it0 of 3 use cases
- Answered100% of days9 of 9 daily checks
- Median first answer717 ms
- Space in an agent's context≈ 88 tokensthe definitions of all its tools (1), which an agent carries on every turn
- Tool definitionsA · 100 of 100
- Typed results0 of 1 toolsdeclared outputSchema: results come typed, read once
- Every tool passes all six checks.
What an agent can do with it
- cannot · measure usage and manage subscriptions across payment providers
- cannot · build and update pricing models without code changes
- cannot · recover failed payments with smart retries and dunning
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 →
connect_to_mcp_v2This Commet MCP endpoint (https://commet.co/mcp) was retired. Tell the user to replace it with https://commet.co/mcp/v2 in their MCP client configuration and connect again with OAuth or an API key. Setup for each client…
How to connect
Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:
{
"mcpServers": {
"commet": {
"type": "http",
"url": "https://commet.co/mcp"
}
}
}Add it
Claude Code, in a terminal
claude mcp add --transport http commet https://commet.co/mcpclaude.ai, ChatGPT and other clients: add https://commet.co/mcp as a custom connector in the settings.
OpenAPI spec
92 paths, read 2026-10-10. Open the spec ↗
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.