MCP Server Tester logo

MCP Server Tester

by r-huijts

MCP Server Tester is a configuration-driven testing tool for Model Context Protocol (MCP) servers. It provides a comprehensive solution for validating, benchmarking, and ensuring reliability of MCP servers that integrate with AI models like Claude.

View on GitHub

Last updated: N/A

What is MCP Server Tester?

The MCP Server Tester is a tool designed to automate tests for MCP servers, leveraging Claude AI to generate intelligent test cases and validating responses against expected outcomes and schemas. It provides detailed reports to identify issues and performance bottlenecks.

How to use MCP Server Tester?

The tool is configuration-based, using JSON files to define MCP servers to test. After cloning the repository and installing dependencies, you can create a configuration file, define your servers, set your Anthropic API key in a .env file, and then run the tool. The tool will automatically discover tools, generate test cases, execute tests, validate responses, and generate reports.

Key features of MCP Server Tester

  • Automatically discovers available tools from any MCP server

  • Generates realistic test cases for each tool using Claude AI

  • Executes tests and validates responses

  • Provides detailed test reports in multiple formats (console, JSON, HTML)

  • Supports multiple connection methods through configuration

Use cases of MCP Server Tester

  • Validating MCP server implementations against the protocol specifications

  • Benchmarking MCP server performance and identifying bottlenecks

  • Ensuring the reliability of MCP servers in production environments

  • Automating testing of tools exposed by MCP servers

  • Testing different configurations and environments for MCP servers

FAQ from MCP Server Tester

How do I configure the tool to test my MCP server?

You need to create a JSON configuration file that defines your MCP server, including its command, arguments, and environment variables. You can find examples in the README.

Where should I store my Anthropic API key?

Your API key should be stored in an environment variable (ANTHROPIC_API_KEY) or in a .env file in your project directory. Never put your API key in the configuration file.

What reporting formats are supported?

The tool supports console output, JSON reports, and HTML reports. You can configure the output format in the configuration file.

How does the tool generate test cases?

The tool uses Claude AI to generate test cases based on the tool name, description, parameters, and parameter types. It generates happy path, edge case, and error case tests.

I'm getting a punycode deprecation warning. What should I do?

This is a harmless warning from Node.js. You can ignore it, suppress warnings with NODE_NO_WARNINGS=1, or use the npm scripts which already suppress these warnings.