{"version":"2.1.274","anchor":"new-mcp-tool-metadata-field-describing-the-serving-mcp-serve","canonical_anchor":"new-mcp-tool-metadata-field-describing-the-serving-mcp-serve","heading":"New MCP tool metadata field describing the serving MCP server","tier":"internal","area":"MCP","scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.274\/e\/new-mcp-tool-metadata-field-describing-the-serving-mcp-serve","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.274","markdown":"### New MCP tool metadata field describing the serving MCP server\n\nMCP tools now carry structured metadata identifying which server and source they came from, for security purposes\n\n**What**\n\nTools provided by MCP (Model Context Protocol) servers now carry structured metadata describing the server that's serving them: the server's configuration key name, and a `source` value drawn from a fixed set of options (`sdk`, `plugin`, `user`, `project`, `local`, `dynamic`, `managed`, `enterprise`, `claudeai`, `agent`) describing where that server's definition came from. The tool-wrapper builder now threads this `source` value through into the tool's metadata.\n\n**Why**\n\nThe metadata explicitly instructs consumers to trust the `source` field, not the tool's name or its `mcp__` prefix, for security purposes. This closes a gap where a tool's name or prefix alone could be spoofed or misleading about where it actually came from.\n\n- Area: MCP\n- Tier: Under the hood\n- Useful: 2\/5\n- Signal: 1\/5"}