Building with Claude

​

Available Subagents

​

Setup

mkdir -p .claude/agents
cp path/to/mcp_eval/data/subagents/*.md .claude/agents/

python -c "import mcp_eval, os; print(os.path.join(os.path.dirname(mcp_eval.__file__), 'data', 'subagents'))"

agents:
  enabled: true
  search_paths:
    # Add the path from the command above
    - "/path/to/site-packages/mcp_eval/data/subagents"
    # Standard locations
    - ".claude/agents"
    - "~/.claude/agents"
  pattern: "*.md"

agents:
  enabled: true
  search_paths:
    - "./src/mcp_eval/data/subagents"  # See: https://github.com/lastmile-ai/mcp-eval/tree/main/src/mcp_eval/data/subagents
  pattern: "*.md"

​

Using Subagents in Claude Code

​

Writing Tests

"Use the mcp-eval-test-writer subagent to create comprehensive tests for my fetch server"

​

Debugging Failures

"Use the mcp-eval-debugger subagent to help me understand why my tests are failing"

​

Configuration Help

"Use the mcp-eval-config-expert subagent to set up my mcpeval.yaml correctly"

​

Using Subagents for Test Generation

1. test-scenario-designer - Designs comprehensive test scenarios
2. test-assertion-refiner - Enhances assertions for better coverage
3. test-code-emitter - Generates syntactically correct Python code

​

Subagent Examples

​

Test Writer Example

# Decorator style
@task("Fetch and validate")
async def test_fetch_validate(agent: Agent, session: Session):
    response = await agent.generate_str("Fetch example.com")
    await session.assert_that(
        Expect.tools.was_called("fetch"),
        response=response
    )

# Pytest style
@pytest.mark.asyncio
async def test_fetch_with_error(mcp_agent, mcp_session):
    response = await mcp_agent.generate_str("Fetch invalid-url")
    await mcp_session.assert_that(
        Expect.content.contains("error"),
        response=response
    )

​

Debugger Example

• Analyzes OTEL traces to find performance bottlenecks
• Identifies assertion failures and suggests fixes
• Troubleshoots configuration problems
• Explains error messages and stack traces

​

Config Expert Example

# Optimized configuration for parallel execution
execution:
  max_concurrency: 10
  timeout_seconds: 60
  fail_fast: true

agents:
  definitions:
    - name: "fetch_agent"
      provider: anthropic
      model: claude-3-5-sonnet-20241022
      instruction: "You are a helpful assistant that can fetch URLs"
      server_names: ["fetch"]

​

Best Practices

1. Use the right subagent for the task - Each subagent is specialized for specific aspects of mcp-eval
2. Combine subagents - Use multiple subagents together for complex tasks
3. Provide context - Give subagents information about your server’s capabilities
4. Review generated code - Subagents provide excellent starting points, but review and customize as needed
5. Keep subagents updated - Pull the latest mcp-eval version for improved subagents

​

Integration with mcp-agent

​

Contributing Subagents

1. Create a markdown file following the format in src/mcp_eval/data/subagents/
2. Include the frontmatter with name, description, and tools
3. Write clear instructions for the subagent’s expertise
4. Test the subagent with real mcp-eval tasks
5. Submit a pull request

​

Related Resources

• Generating Tests with LLMs - Automated test generation
• Agent Configuration - Configure agents for testing
• Best Practices - General mcp-eval best practices
• GitHub: Subagents Source - View all subagent definitions on GitHub