GitHub - atototo/api-lab-mcp: api test mcp (original) (raw)

API Lab MCP ๐Ÿงช

npm version License: MIT MCP Compatible Claude Desktop

Transform Claude into your AI-powered API testing laboratory. Test, debug, and document APIs through natural conversation.

๐ŸŒŸ Why API Lab MCP?

Stop switching between tools. Stop writing repetitive test scripts. Start having conversations with your APIs.

The Problem: Traditional API testing tools require constant context switching, manual script writing, and repetitive workflows that slow down development.

The Solution: API Lab MCP integrates directly with Claude Desktop and Claude Code, allowing you to test APIs through natural language while you code. No more jumping between Postman, terminal, and your IDE.

What makes it different?

โœจ Key Features

๐Ÿš€ Quick Start (30 seconds)

For Claude Code

Install globally

npm install -g api-lab-mcp

Add to Claude Code

claude mcp add api-lab-mcp api-lab-mcp

Start testing!

Tell Claude: "Test my API at localhost:3000"

For Claude Desktop

Install via npm

npm install -g api-lab-mcp

Then add to Claude Desktop config (see Installation section)

That's it! You're ready to test APIs with Claude.

๐Ÿ“ธ Live Demo with Claude Desktop

Watch API Lab MCP in action with Claude Desktop - testing real APIs through conversation:

Claude Desktop Demo

Real Results from Claude Desktop

Claude Desktop Results

"Test your APIs through natural conversation - in any language you prefer."

๐Ÿ’ก Use Cases

For Development Teams

For QA Engineers

For DevOps

๐Ÿ’ฌ Real-World Examples

Test a REST API

You: "Test the GitHub API to get my user info"
Claude: *Tests GET https://api.github.com/user with your token*

Debug a Failed Request

You: "Why is my login endpoint returning 401?"
Claude: *Analyzes headers, body, and suggests missing auth token*

Session-based Authentication

You: "Test my app with session cookie JSESSIONID=ABC123"
Claude: *Configures session and tests authenticated endpoints*

Performance Testing

You: "Check if all my endpoints respond under 200ms"
Claude: *Runs performance tests and generates report*

Generate Tests from Swagger

You: "Create tests from my OpenAPI spec at /api/docs"
Claude: *Generates comprehensive test suite automatically*

๐Ÿ”ง Installation

Claude Code Installation

Method 1: Global install (recommended)

npm install -g api-lab-mcp claude mcp add api-lab-mcp api-lab-mcp

Method 2: Using npx (no install needed)

claude mcp add api-lab-mcp "npx -y api-lab-mcp"

Method 3: Local development

git clone https://github.com/atototo/api-lab-mcp.git cd api-lab-mcp npm install && npm run build claude mcp add api-lab-local "node $(pwd)/dist/mcp/server.js"

Claude Desktop Installation

macOS/Linux Setup

  1. Install the package:

npm install -g api-lab-mcp

  1. Find your config file:

macOS

open ~/Library/Application\ Support/Claude/

Linux

open ~/.config/claude/

  1. Edit claude_desktop_config.json:

{ "mcpServers": { "api-lab-mcp": { "command": "npx", "args": ["-y", "api-lab-mcp"] } } }

  1. Restart Claude Desktop Windows Setup
  2. Install the package:

npm install -g api-lab-mcp

  1. Open config folder:

explorer %APPDATA%\Claude

  1. Edit claude_desktop_config.json:

{ "mcpServers": { "api-lab-mcp": { "command": "npx.cmd", "args": ["-y", "api-lab-mcp"] } } }

  1. Restart Claude Desktop Docker Setup

FROM node:20-alpine RUN npm install -g api-lab-mcp EXPOSE 3000 CMD ["api-lab-mcp", "--http-mode"]

Run with:

docker build -t api-lab-mcp . docker run -p 3000:3000 api-lab-mcp

Verify Installation

After installation, ask Claude:

"Can you test the API at https://api.github.com?"

If Claude can test the API, installation was successful!

๐Ÿ—๏ธ For Developers

Local Development Workflow

API Lab MCP supercharges your local development:

Real-time API Testing

"Test POST /api/users on localhost:3000 with mock data"

Smart Debugging

"Why is this endpoint slow? Profile the response time"

Automatic Documentation

"Generate README docs from these test results"

Pre-deployment Validation

"Run health checks on all endpoints before I deploy"

Development Setup

Clone the repository

git clone https://github.com/atototo/api-lab-mcp.git cd api-lab-mcp

Install dependencies

npm install

Run in development mode

npm run dev

Build for production

npm run build

Run tests

npm test

Architecture

api-lab-mcp/
โ”œโ”€โ”€ src/
โ”‚   โ”œโ”€โ”€ mcp/              # MCP server implementation
โ”‚   โ”œโ”€โ”€ core/             # Core business logic
โ”‚   โ”œโ”€โ”€ http/             # HTTP client layer
โ”‚   โ””โ”€โ”€ types/            # TypeScript definitions
โ”œโ”€โ”€ tests/                # Test suites
โ””โ”€โ”€ docs/                 # Documentation

๐Ÿ“Š How It Compares

Feature API Lab MCP Postman Insomnia Thunder Client
AI-Powered Testing โœ… Native โŒ โŒ โŒ
Natural Language โœ… โŒ โŒ โŒ
Claude Integration โœ… โŒ โŒ โŒ
Zero Setup โœ… โŒ โŒ โš ๏ธ
Session Management โœ… โœ… โœ… โœ…
OpenAPI Support โœ… โœ… โœ… โš ๏ธ
MCP Protocol โœ… โŒ โŒ โŒ
Conversational UI โœ… โŒ โŒ โŒ
Auto Documentation โœ… โš ๏ธ โš ๏ธ โŒ
Free & Open Source โœ… โš ๏ธ โš ๏ธ โœ…

๐Ÿ“š Documentation

Core Tools

test_http_endpoint

Test any HTTP endpoint with full customization:

test_with_assertions

Advanced testing with intelligent response validation:

test_with_session

Session-based authentication for complex flows:

batch_test

Run multiple API tests efficiently:

analyze_api_spec

Extract and understand OpenAPI/Swagger specifications:

generate_test_scenarios

AI-powered test generation from specs:

Advanced Features

Configuration Options

API Lab MCP works out of the box with zero configuration. You can customize behavior through tool parameters:

Tool-level Options

Environment Variables (HTTP Server Mode)

Common Issues & Solutions

Installation Issues

Connection Issues

Testing Issues

Full API Documentation โ†’

๐Ÿค Contributing

We love contributions! Whether it's a bug report, feature request, or pull request, all contributions are welcome.

Fork and clone

git clone https://github.com/YOUR_USERNAME/api-lab-mcp.git

Create your feature branch

git checkout -b feature/amazing-feature

Make your changes and commit

git commit -m 'Add amazing feature'

Push and create PR

git push origin feature/amazing-feature

See CONTRIBUTING.md for detailed guidelines.

๐ŸŒŸ Success Stories

"API Lab MCP reduced our API testing time by 70%. We now test as we code, right in Claude." - Senior Developer at TechCorp

"The natural language interface is a game-changer. Junior developers can now write complex API tests." - CTO at StartupXYZ

"We replaced three different tools with just API Lab MCP. It's that powerful." - DevOps Lead

๐Ÿ“ˆ Roadmap

๐Ÿ›Ÿ Support

๐Ÿ“„ License

MIT ยฉ 2024 atototo


If API Lab MCP helps your development workflow, please consider giving it a โญ

Star on GitHub

Built with โค๏ธ for developers who value their time