{"version":"2.1.268","anchor":"mcp-tool-call-now-merges-additional-call-metadata-via-dpejm","canonical_anchor":"mcp-tool-call-now-merges-additional-call-metadata-via-dpejm","heading":"MCP tool call now merges additional call metadata via DPe\/Jmt\/Xbt","tier":"internal","area":"MCP","scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.268\/e\/mcp-tool-call-now-merges-additional-call-metadata-via-dpejm","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.268","markdown":"### MCP tool call now merges additional call metadata via DPe\/Jmt\/Xbt\n\nMCP tool calls can now attach extra metadata fields alongside the tool-use ID, behind a gate\n\n**Unclear.** What the extra metadata fields contain and what they're used for is not stated.\n\n**What**\n\nWhen Claude Code calls an MCP (Model Context Protocol) tool \u2014 a tool provided by an external server rather than built in \u2014 it sends along a small metadata payload with the tool-use ID. Now, when an internal condition is met, extra fields are merged into that metadata payload as well. Previously the payload only ever contained the tool-use ID.\n\n**Why**\n\nThis lets Claude Code pass additional context to MCP tool servers in some sessions, though the finding doesn't specify what that extra context contains or affects.\n\n- Area: MCP\n- Tier: Under the hood\n- Useful: 1\/5\n- Signal: 1\/5"}