{"version":"2.1.242","anchor":"mocked-mcp-servers-register-under-the-real-server-name-and-d","canonical_anchor":"mocked-mcp-servers-register-under-the-real-server-name-and-d","heading":"Mocked MCP servers register under the real server name and deny everything else","tier":"use","area":"Plugin Eval","scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.242\/e\/mocked-mcp-servers-register-under-the-real-server-name-and-d","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.242","markdown":"### Mocked MCP servers register under the real server name and deny everything else\n\nMock servers replace real ones by name, allow mocked tools and deny the rest; a mock_calls grader is added.\n\n**What**\n\nThe stand-in servers take the place of the plugin's own MCP servers under the same name, auto-allow the tools that have mock files, and deny every other tool on that server. A new grader target, `mock_calls`, grades what the plugin asked the server to do rather than what it said.\n\n**Details**\n\n- A case can carry its own `mocks\/` directory, and `mocks\/` becomes a reserved name inside eval directories.\n- Frontmatter supports `expect:` input assertions that abort the run on violation, and `error: true` to return a tool error.\n- Each run's JSON gains a `mocks` block with per-server responder kinds, a call tally of total\/errors\/unmocked, and warnings, plus an `aborted` record.\n- Failures are reported through telemetry key `cli_plugin_eval_mocks` with outcomes standin_registration, standin_identity, standin_tools_missing, standin_integrity and aborted_by_mock.\n- `claude plugin eval` is itself early access, enabled per organisation or by an env var, and prints that it is unavailable otherwise.\n\n**Evidence**\n\n`mock_calls`, `--mocks <mode>`, `Mock stand-ins for MCP servers, from <eval dir>\/mocks\/`\n\n- Area: Plugin Eval\n- Names: `mock_calls`\n- Tier: Use it now\n- Useful: 3\/5\n- Signal: 3\/5"}