npm install mcp-evals

name: Run MCP Evaluations
on:
  pull_request:
    types: [opened, synchronize, reopened]
jobs:
  evaluate:
    runs-on: ubuntu-latest
    permissions:
      contents: read
      pull-requests: write
    steps:
      - uses: actions/checkout@v4
      
      - name: Setup Node.js
        uses: actions/setup-node@v4
        with:
          node-version: '20'
          
      - name: Install dependencies
        run: npm install
        
      - name: Run MCP Evaluations
        uses: mclenhard/mcp-evals@v1.0.9
        with:
          evals_path: 'src/evals/evals.ts'    # Can also use .yaml files
          server_path: 'src/index.ts'
          openai_api_key: ${{ secrets.OPENAI_API_KEY }}
          model: 'gpt-4'  # Optional, defaults to gpt-4

import { EvalConfig } from 'mcp-evals';
import { openai } from "@ai-sdk/openai";
import { grade, EvalFunction} from "mcp-evals";

const weatherEval: EvalFunction = {
    name: 'Weather Tool Evaluation',
    description: 'Evaluates the accuracy and completeness of weather information retrieval',
    run: async () => {
      const result = await grade(openai("gpt-4"), "What is the weather in New York?");
      return JSON.parse(result);
    }
};
const config: EvalConfig = {
    model: openai("gpt-4"),
    evals: [weatherEval]
  };
  
  export default config;
  
  export const evals = [
    weatherEval,
    // add other evals here
]; 

# Model configuration
model:
  provider: openai     # 'openai' or 'anthropic'
  name: gpt-4o        # Model name
  # api_key: sk-...   # Optional, uses OPENAI_API_KEY env var by default

# List of evaluations to run
evals:
  - name: weather_query_basic
    description: Test basic weather information retrieval
    prompt: "What is the current weather in San Francisco?"
    expected_result: "Should return current weather data for San Francisco including temperature, conditions, etc."

  - name: weather_forecast
    description: Test weather forecast functionality
    prompt: "Can you give me the 3-day weather forecast for Seattle?"
    expected_result: "Should return a multi-day forecast for Seattle"

  - name: invalid_location
    description: Test handling of invalid location requests
    prompt: "What's the weather in Atlantis?"
    expected_result: "Should handle invalid location gracefully with appropriate error message"

# Using TypeScript configuration
npx mcp-eval path/to/your/evals.ts path/to/your/server.ts

# Using YAML configuration
npx mcp-eval path/to/your/evals.yaml path/to/your/server.ts

interface EvalResult {
  accuracy: number;        // Score from 1-5
  completeness: number;    // Score from 1-5
  relevance: number;       // Score from 1-5
  clarity: number;         // Score from 1-5
  reasoning: number;       // Score from 1-5
  overall_comments: string; // Summary of strengths and weaknesses
}

import { metrics } from 'mcp-evals';
metrics.initialize(9090, { enableTracing: true, otelEndpoint: 'http://localhost:4318/v1/traces' });

docker-compose up -d