Source Intelligence

DisclaimerUnofficial, and not affiliated with Anthropic. Nearly all of this is read straight out of what ships: npm bundles, captured prompts, published docs. Anthropic's own notes go in verbatim, marked as theirs. The rest is my reading, and every entry carries the strings behind it. If one looks wrong, vote it down and say why.

All of v2.1.248 Home All releases olderv2.1.247 v2.1.250newer
Claude Code v2.1.248

MCP capability lists are fetched once per server

You'll notice
Useful3 Signal2
MCP

MCP tool and resource listings are fetched once per server, with classified failures.

What

Tool, resource, prompt and resource-template listings are now cached per server rather than re-fetched, and failures are classified instead of being opaque.

Details
  • Caching is keyed on server name plus config, with the cache entry deleted on failure so the next attempt retries.
  • Failures set needs-auth and bearer-rejected flags on the client and map JSON-RPC codes to reasons such as mcp_list_tools_timeout.
Evidence

tools/list 401/403 on claude.ai proxy \u2014 flagging needs-auth

Strings lifted out of the shipped bundle, so the claim above can be checked against them.

See this entry in the whole of v2.1.248 →