{"version":"2.1.292","anchor":"mcp-idle-timeout-abort-message-now-reports-the-right-numbers","canonical_anchor":"mcp-idle-timeout-abort-message-now-reports-the-right-numbers","heading":"MCP idle-timeout message now shows the right times","tier":"notice","area":"MCP","scope":"individual","heads_up":false,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.292\/e\/mcp-idle-timeout-abort-message-now-reports-the-right-numbers","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.292","markdown":"### MCP idle-timeout message now shows the right times\n\nWhen an MCP tool is stopped for going idle too long, the message now shows the same idle time and timeout that actually triggered it\n\n**What**\n\nMCP servers are outside programs that give Claude extra tools. If a tool call goes too long with no response or progress update, Claude Code stops it and shows how long it waited and what the timeout was. Both numbers were taken from different values than the ones the check used. They now use the same values, so the message matches what caused the stop.\n\n**Why**\n\nIf you are working out why an MCP tool timed out, the idle time and timeout shown are now accurate.\n\n- Area: MCP\n- Tier: You'll notice\n- Useful: 1\/5\n- Signal: 1\/5\n- Scope: individual\n- Heads-up: no"}