{"version":"2.1.269","anchor":"concurrent-mcp-reconnect-requests-for-the-same-server-now-wa","canonical_anchor":"concurrent-mcp-reconnect-requests-for-the-same-server-now-wa","heading":"Concurrent mcp_reconnect requests for the same server now wait on each other","tier":"notice","area":"MCP","scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.269\/e\/concurrent-mcp-reconnect-requests-for-the-same-server-now-wa","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.269","markdown":"### Concurrent mcp_reconnect requests for the same server now wait on each other\n\nRepeated MCP reconnect requests for the same server now wait for the first one instead of overlapping\n\n**What**\n\nWhen Claude Code receives an `mcp_reconnect` request (used to reconnect to an MCP server, a connector that gives Claude Code access to external tools or data), it now checks whether a reconnect to that same server is already in progress. If so, it waits for that existing attempt to finish before starting a new one, instead of running both at once.\n\n**Why**\n\nThis avoids two reconnect attempts to the same MCP server racing each other, which could otherwise leave the connection in an inconsistent state.\n\n- Area: MCP\n- Names: `mcp_reconnect`\n- Tier: You'll notice\n- Useful: 2\/5\n- Signal: 1\/5"}