{"version":"2.1.268","anchor":"mcp-toolnotification-names-are-now-sanitized-before-logging","canonical_anchor":"mcp-toolnotification-names-are-now-sanitized-before-logging","heading":"MCP tool\/notification names are now sanitized before logging","tier":"internal","area":"MCP","scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.268\/e\/mcp-toolnotification-names-are-now-sanitized-before-logging","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.268","markdown":"### MCP tool\/notification names are now sanitized before logging\n\nMCP tool and notification names are now truncated and sanitized before appearing in logs\n\n**What**\n\nWhen Claude Code's internal MCP (Model Context Protocol) host logs which tool is executing or which notification method was received, it now truncates the name to 64 characters and converts it to a safe JSON string before writing it to the debug or info log, instead of inserting the raw name directly.\n\n**Why**\n\nThis prevents an MCP server from injecting unexpected or oversized content into Claude Code's logs via a crafted tool or notification name.\n\n- Area: MCP\n- Tier: Under the hood\n- Useful: 1\/5\n- Signal: 1\/5"}