mcpwatch

How the index checks servers

If you saw mcpwatch-index in your logs, this page explains what it did and how to opt out.

What we send

Once a day, for each remote endpoint a publisher listed in the official MCP registry, the indexer sends the same requests any MCP client sends when it connects:

  1. initialize (the standard MCP handshake)
  2. notifications/initialized
  3. tools/list (reads the tool names, descriptions and input schemas)
  4. an HTTP DELETE with the session id, to close the session

That's all. We never call a tool, never send credentials, never guess passwords and never fuzz. If your endpoint asks for authentication, we stop and record "requires auth".

Limits we keep

Opt out

Open an issue titled "Opt out: <your registry server name or hostname>" at github.com/anardimontlv/mcpwatch. Opted-out servers are no longer contacted. Their page keeps only the checks based on public registry data and says "not probed (owner opt-out)"; opting out never lowers a grade.

Why we do this

Developers connect AI agents to MCP servers, and an agent reads tool descriptions as instructions. Publishing which tools a public endpoint exposes, and noticing when they change, helps people decide what to trust. The method is documented in how it works, and the indexer's source code is public.