{"version":"2.1.227","anchor":"mcp-connection-timeouts-are-retried-and-never-undercut-the-g","canonical_anchor":"mcp-connection-timeouts-are-retried-and-never-undercut-the-g","heading":"MCP connection timeouts are retried and never undercut the global timeout","tier":"notice","area":"MCP","scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.227\/e\/mcp-connection-timeouts-are-retried-and-never-undercut-the-g","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.227","markdown":"### MCP connection timeouts are retried and never undercut the global timeout\n\nMCP connect timeouts now respect the global timeout and get retried instead of failing.\n\n**What**\n\nThe 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.\n\n**Details**\n\n- the SDK's own `RequestTimeout` error is mapped onto the same `CONNECT_TIMEOUT` code so it retries too\n\n**Evidence**\n\n`tengu_mcp_connect_timeout_retry`\n\n- Flag `tengu_mcp_connect_timeout_retry`: Not enough to say (read for one account on one subscription tier against v2.1.227; this account: no value returned, anonymous baseline: no value returned, compiled default: 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.\n- Area: MCP\n- Tier: You'll notice\n- Useful: 4\/5\n- Signal: 3\/5"}