Frequently asked questions about mcp-eval, servers, agents, and configuration.
mcp-eval server add
or import from mcp.json
/ DXT. See Quickstart and CLI Reference.
@with_agent(...)
above @task(...)
when used together.
mcp-eval run tests/test_file.py::test_func
or mcp-eval run dataset path.yaml
.
mcpeval.yaml
and secrets.
Dataset.evaluate(..., max_concurrency=N)
enables parallel case execution.