{"version":"2.1.232","anchor":"mcp-connections-record-how-they-negotiated-and-treat-a-probe","canonical_anchor":"mcp-connections-record-how-they-negotiated-and-treat-a-probe","heading":"MCP connections record how they negotiated, and treat a probe timeout as a fallback","tier":"notice","area":"MCP","scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.232\/e\/mcp-connections-record-how-they-negotiated-and-treat-a-probe","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.232","markdown":"### MCP connections record how they negotiated, and treat a probe timeout as a fallback\n\nAn MCP probe that times out is treated as a fallback rather than a failed connection.\n\n**What**\n\nMCP connect success and failure events now record which negotiation mode was used and whether the connection had to fall back after probing. In automatic negotiation mode, a request timeout during the Anthropic-side probe is now treated as a fallback case instead of a hard connection failure.\n\n**Evidence**\n\n`_anthropicProbeTimedOut`\n\n- Area: MCP\n- Tier: You'll notice\n- Useful: 4\/5\n- Signal: 3\/5"}