www.mcpjam.com

MCPJam inspector is an open source testing platform for MCP servers. It’s a great place to start evaluating an MCP server by inspecting the protocol handshake and getting a deterministic list of tools, resources, prompts from the server.

Key Features

Feature	Description
Protocol handshake testing	Test your MCP server's tools, resources, prompts, elicitation, and OAuth 2. MCPJam is compliant with the latest MCP specs.
All transports supported	Connect to any MCP server. MCPJam inspector supports STDIO, SSE, and Streamable HTTP transports.
LLM Playground	Integrated chat playground with OpenAI, Anthropic Claude, and Ollama model support. Test how your MCP server would behave against an LLM
Evals testing	Simulate users flows to catch security vulnerabilities and performance regressions before your server hits production.
Multiple server connections	Connect to multiple MCP servers. Save configurations. Upgraded UI/UX for modern dev experience.
MCP-UI and OpenAI Apps SDK support	Test your MCP server's implementation of MCP-UI or OpenAI Apps SDK

📸 Screenshots

LLM Playground

Evals and pen testing

Connect with OAuth

🎉 Open AI Apps SDK support now in beta!

Start up the MCPJam inspector in beta:

npx @mcpjam/inspector@beta

Developing with Apps SDK is pretty restricted right now as it requires ChatGPT developer mode access and an OpenAI partner to approve access. We wanted to make that more accessible for developers today by putting it in an open source project, give y’all a head start.

Test your Apps SDK app with:

• Tools tab. Deterministically call tools and view your UI
• LLM playground to see your Apps SDK UI in a chat environment

The feature is in beta, and still needs polishing. Please report any bugs in the issues tab. We encourage the community to contibute!

🚀 Quick Start

Start up the MCPJam inspector:

npx @mcpjam/inspector@latest

Other commands:

# Launch with custom port
npx @mcpjam/inspector@latest --port 4000

# Shortcut for starting MCPJam and an Ollama model
npx @mcpjam/inspector@latest --ollama llama3.2

🐳 Docker

Run MCPJam Inspector using Docker:

# Run the latest version from Docker Hub
docker run -p 3001:3001 mcpjam/mcp-inspector:latest

# Or run in the background
docker run -d -p 3001:3001 --name mcp-inspector mcpjam/mcp-inspector:latest

The application will be available at http://localhost:3001.

Connecting to MCP servers

mcp.json

You can import your mcp.json MCP server configs from Claude Desktop and Cursor with the command:

npx @mcpjam/inspector@latest --config mcp.json

STDIO

Note: Always use global file paths

# Local FastMCP STDIO example
npx @mcpjam/inspector@latest uv run fastmcp run /Users/matt8p/demo/src/server.py
# Local Node example
npx @mcpjam/inspector@latest npx -y /Users/matt8p/demo-ts/dist/index.js

SSE / Streamable HTTP

Spin up the MCPJam inspector

npx @mcpjam/inspector@latest

In the UI "MCP Servers" tab, click add server, select HTTP, then paste in your server URL

Requirements

🛠️ Development

Local Development Setup

# Clone the repository
git clone https://github.com/mcpjam/inspector.git
cd inspector

# Install dependencies
npm install

# Start development server
npm run dev

The development server will start at http://localhost:3000 with hot reloading enabled.

Build for Production

# Build the application
npm run build

# Start production server
npm run start

Available Scripts

Script	Description
npm run dev	Start Next.js development server with Turbopack
npm run build	Build the application for production
npm run start	Start the production server
npm run lint	Run ESLint code linting
npm run prettier-fix	Format code with Prettier

---

🤝 Contributing

We welcome contributions to MCPJam Inspector V1! Please read our CONTRIBUTING.md for development guidelines and best practices.

Development Workflow

1. Fork the repository
2. Create a feature branch (git checkout -b feature/amazing-feature)
3. Develop your changes with proper testing
4. Format code with npm run prettier-fix
5. Lint code with npm run lint
6. Commit your changes (git commit -m 'Add amazing feature')
7. Push to your branch (git push origin feature/amazing-feature)
8. Open a Pull Request

📚 Resources

• 💬 Discord: Join the MCPJam Community
• 📖 MCP Protocol: Model Context Protocol Documentation
• 🔧 Mastra Framework: Mastra MCP Integration
• 🤖 AI SDK: Vercel AI SDK

---

📄 License

This project is licensed under the Apache License 2.0 - see the LICENSE file for details.

---

MCPJam Inspector V1 • Built with Hono.js and ❤️ for the MCP community

🌐 Website • 📖 Docs • 🐛 Issues