{"version":"2.1.238","anchor":"a-slow-mcp-reconnect-can-no-longer-overwrite-the-current-ser","canonical_anchor":"a-slow-mcp-reconnect-can-no-longer-overwrite-the-current-ser","heading":"A slow MCP reconnect can no longer overwrite the current server state","tier":"notice","area":"MCP","scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.238\/e\/a-slow-mcp-reconnect-can-no-longer-overwrite-the-current-ser","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.238","markdown":"### A slow MCP reconnect can no longer overwrite the current server state\n\nA late MCP reconnect can no longer clobber the tools and prompts of the connection you're using.\n\n**What**\n\nWhen an MCP server connection is re-established, Claude Code now checks whether a newer connection attempt has started since. If so it closes the connection it just made and publishes nothing, so a late-arriving reconnect cannot replace the tools, prompts and resources of the connection you are actually using.\n\n**Details**\n\n- The check runs after connecting and again after each `list_changed` refresh.\n- Stale connections are torn down through `detachAndCloseConnection`.\n\n**Evidence**\n\n`detachAndCloseConnection`\n\n- Area: MCP\n- Tier: You'll notice\n- Useful: 4\/5\n- Signal: 2\/5"}