{"version":"2.1.132","anchor":"mcp-connection-resilience","canonical_anchor":"mcp-connection-resilience","heading":"MCP Connection Resilience","tier":null,"area":null,"scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.132\/e\/mcp-connection-resilience","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.132","markdown":"### MCP Connection Resilience\n\nRemote MCP retry behavior now logs recovery and stops retrying once failed remote servers recover. MCP stdio transports also detect excessive non-protocol stdout and disconnect before unbounded memory growth.\n\n**Evidence**\n\nMCP retry and stdout overflow handling (search for `\"[MCP] Retry: all remote servers recovered, stopping\"` and `\"StdoutOverflowError\"`)"}