{"version":"2.1.246","anchor":"mcp-servers-that-dropped-before-wiring-now-reconnect","canonical_anchor":"mcp-servers-that-dropped-before-wiring-now-reconnect","heading":"MCP servers that dropped before wiring now reconnect","tier":"notice","area":"MCP","scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.246\/e\/mcp-servers-that-dropped-before-wiring-now-reconnect","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.246","markdown":"### MCP servers that dropped before wiring now reconnect\n\nAn MCP server that dropped before reconnect wiring finished now reconnects right away.\n\n**What**\n\nIf an MCP server's connection had already closed by the time the reconnect handler was attached, the reconnect is now scheduled immediately instead of waiting for a close event that will never arrive.\n\n**Details**\n\n- The log line distinguishes a transport that closed later from one that \"had already closed when wired\".\n- Reconnects now emit telemetry: success with the attempt count and whether it was found already closed, and failure as either `needs_auth` or `exhausted` once the attempt cap is reached.\n\n**Evidence**\n\n`had already closed when wired`\n\n- Area: MCP\n- Tier: You'll notice\n- Useful: 3\/5\n- Signal: 1\/5"}