What
Browsing an MCP server's tools in /mcp now shows a dim note under any tool whose description exceeds 2048 characters, telling you the model only receives roughly the first part of it. Useful when a server's tool is being ignored or misused.
Details
- The 2048 cap is a constant stored alongside the other MCP protocol constants.
- The note is assembled from a fixed prefix, the number, and a suffix; no setting hides it.
Evidence
The model receives only about the first
Strings lifted out of the shipped bundle, so the claim above can be checked against them.
Names in the bundle/mcp
The entry above is what we published on the day. These lines were added later, as Anthropic's own pages caught up, and they sit beside the original rather than replacing it.
Added since
A small documentation edit on Channels reference touched a line naming /mcp after this was published.
* **`curl` succeeds but nothing reaches Claude**: run `/mcp` in your session to check the server's status. A `failed` status usually means a dependency or import error in your server file. To see the stderr trace, restart with `claude --de…channels-reference see the edit
Confirmed since
Anthropic's documentation has since written up /mcp, on Third party connectors with remote MCP.
**MCP server URL**: the HTTPS address where the server accepts MCP requests, for example `https://mcp.example.com/mcp`. After you continue, Claude checks the URL and pre-fills the authentication settings it detects, marked "Detected."connectors/custom/remote-mcp see the edit
Two sources agreeTwo things we can check say the same as this entry.
Anthropic's documentation agrees
Anthropic's documentation has since written up /mcp, on Third party connectors with remote MCP.
Anthropic's release notes agree
Fixed /mcp listing a project .mcp.json entry that declares the claude.ai connector type under the trusted "claude.ai" heading; it now…