{"version":"2.1.221","anchor":"new-mcp-policy-predicate-telemetry-for-allowedmcpservers-mat","canonical_anchor":"new-mcp-policy-predicate-telemetry-for-allowedmcpservers-mat","heading":"New MCP policy-predicate telemetry for allowedMcpServers matching","tier":"internal","area":"MCP","scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.221\/e\/new-mcp-policy-predicate-telemetry-for-allowedmcpservers-mat","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.221","markdown":"### New MCP policy-predicate telemetry for allowedMcpServers matching\n\nClaude now tracks whether your allowed-MCP-server rules could actually be evaluated.\n\n**What**\n\nMatching a server against allowedMcpServers now reports, once per session, whether the predicate could be evaluated.\n\n**Details**\n\n- A successful match reports \"ok\".\n- Unresolved variables in a policy command or URL report \"missing_policy_var\".\n- An unsafe URL expansion reports \"unsafe_expansion\".\n- All reported under the metric name mcp_policy_predicate.\n\n**Evidence**\n\n`mcp_policy_predicate`\n\n- Area: MCP\n- Names: `allowedMcpServers`\n- Tier: Under the hood\n- Useful: 2\/5\n- Signal: 0\/5"}