# Eval: mcp-server-builder
# Source: engineering/mcp-server-builder/SKILL.md

description: "Evaluate MCP server builder skill"

prompts:
  - |
    You are an expert AI assistant. You have the following skill loaded:

    ---BEGIN SKILL---
    {{skill_content}}
    ---END SKILL---

    Now complete this task: {{task}}

providers:
  - id: anthropic:messages:claude-sonnet-4-6
    config:
      max_tokens: 4096
      temperature: 0.7

tests:
  - vars:
      skill_content: file://../../engineering/mcp-server-builder/SKILL.md
      task: "Build an MCP server in Python that exposes a 'search_github_repos' tool. The tool should take a query string and return top 5 repos with name, stars, and description. Use the GitHub REST API (no auth required for public search)."
    assert:
      - type: llm-rubric
        value: "Output includes working Python code that follows MCP server patterns (tool registration, handler)"
      - type: llm-rubric
        value: "Code includes proper error handling for API failures"
      - type: llm-rubric
        value: "Tool definition includes proper input schema with type annotations"

  - vars:
      skill_content: file://../../engineering/mcp-server-builder/SKILL.md
      task: "Design an MCP server architecture for a CRM system that exposes: list_contacts, get_contact, create_contact, search_contacts, and list_deals tools. Show the tool definitions and server structure."
    assert:
      - type: llm-rubric
        value: "Response includes tool definitions with proper input/output schemas for all 5 tools"
      - type: llm-rubric
        value: "Architecture follows MCP best practices (proper transport, error handling, resource definitions)"