The connect timeout for an MCP server is now the larger of that server's own value and the global MCP timeout, so a small per-server value can no longer make connections fail early. Connection timeouts are tagged CONNECT_TIMEOUT and retried instead of failing outright, including timeouts raised by the MCP SDK itself. Controlled by the tengu_mcp_connect_timeout_retry flag, which is on unless the server turns it off.
- the SDK's own
RequestTimeouterror is mapped onto the sameCONNECT_TIMEOUTcode so it retries too
tengu_mcp_connect_timeout_retry
Strings lifted out of the shipped bundle, so the claim above can be checked against them.
tengu_mcp_connect_timeout_retry Not enough to sayNothing here resolved what this flag was doing on this version, so nothing here should be read as on or off.
This account: no value returned · anonymous baseline: no value returned · compiled default in v2.1.227: on
These values were read against a different version of Claude Code, so treat them as the nearest reading available instead of one taken on this release.
Read once, for one account on one subscription tier, against v2.1.227. It isn't a statement about your account. What a flag value here can and cannot tell you
New in this build: tengu_mcp_connect_timeout_retry