{"version":"2.1.274","anchor":"mcp-tool-descriptions-carry-provenance-source-into-the-r","canonical_anchor":"mcp-tool-descriptions-carry-provenance-source-into-the-r","heading":"MCP tool descriptions carry provenance ('source') into the render payload","tier":"internal","area":"MCP","scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.274\/e\/mcp-tool-descriptions-carry-provenance-source-into-the-r","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.274","markdown":"### MCP tool descriptions carry provenance ('source') into the render payload\n\nMCP tool data sent to the UI now includes where each MCP client came from\n\n**Unclear.** It's unclear whether or how this source information is currently surfaced to the user in the interface.\n\n**What**\n\nWhen Claude Code passes information about connected MCP clients (Model Context Protocol servers providing extra tools) into the data used to render the interface, each client entry now includes a `source` field alongside its `name` and `type`, computed by a new internal helper.\n\n**Why**\n\nThis adds provenance information about MCP tools that the interface (or other consumers of this data) can use, though the finding doesn't specify what visibly changes for users yet.\n\n- Area: MCP\n- Tier: Under the hood\n- Useful: 1\/5\n- Signal: 1\/5"}