{"version":"2.1.269","anchor":"eval-mocks-tooling-now-withholds-mock-mcp-stand-ins-under-ma","canonical_anchor":"eval-mocks-tooling-now-withholds-mock-mcp-stand-ins-under-ma","heading":"Eval-mocks tooling now withholds mock MCP stand-ins under managed-mcp.json lockdown","tier":"internal","area":"Plugin Eval","scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.269\/e\/eval-mocks-tooling-now-withholds-mock-mcp-stand-ins-under-ma","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.269","markdown":"### Eval-mocks tooling now withholds mock MCP stand-ins under managed-mcp.json lockdown\n\nEval-mocks testing tool now respects managed-mcp.json lockdown by withholding mock MCP servers\n\n**What**\n\nClaude Code's internal eval-mocks tool, used for testing skills and plugins, now checks whether an enterprise `managed-mcp.json` file with exclusive control over MCP (Model Context Protocol) servers is present. If it is, the tool filters out any mock MCP server stand-ins instead of registering them, and logs a warning noting that plugin servers won't load in the child process either.\n\n**Why**\n\nThis keeps the test harness consistent with how a real session behaves under enterprise MCP lockdown, so tests don't register mock servers that would actually be blocked in production.\n\n- Area: Plugin Eval\n- Tier: Under the hood\n- Useful: 1\/5\n- Signal: 1\/5"}