AutoSpectra MCP Server

<div align="center"> <img src="assets/logo.png" alt="AutoSpectra Logo" width="200"> <p><strong>All-In-One Automation Platform for AI Agents: Browser, API Testing, and More</strong></p>

smithery badge

</div>

AutoSpectra is a comprehensive MCP (Model Context Protocol) server that provides complete automation and testing capabilities for any AI agent. From browser automation and API testing to debugging tools and mock services, AutoSpectra offers a full suite of tools that integrate seamlessly with any MCP-compatible system, including but not limited to Claude, ChatGPT, Gemini, and Perplexity.

Features

🌐 Browser Automation: Navigate, click, type, extract data, and take screenshots
🔌 API Testing Tools: Make HTTP/GraphQL requests, validate schemas, create mock APIs
🧪 Testing Framework: End-to-end testing, accessibility testing, and visual validation
🐞 Debugging Capabilities: Interactive debug sessions with step-by-step execution
🤖 AI Agent Compatibility: Works with any AI agent supporting the MCP protocol
👁️ Visible Browser Mode: Debug with visible browsers or run headless for efficiency
🔄 Self-Healing Selectors: Robust element selection that adapts to changes
💻 Claude Computer Use: Integration with Anthropic's Claude computer capabilities

Installation

# Clone the repository
git clone https://github.com/your-username/autospectra-mcp-server.git
cd autospectra-mcp-server

# Install dependencies
npm install

# Build the project
npm run build

Environment Setup

Create a .env file in the root directory with the following variables:

# Server configuration
PORT=3000
DEBUG=true
HTTP_SERVER=true

# API Keys
ANTHROPIC_API_KEY=your-anthropic-api-key

# Playwright configuration
HEADLESS=false
SLOW_MO=50

# Output directory
OUTPUT_DIR=./output

Usage

Starting the Server

# Start the server
npm start

# Or start in development mode
npm run dev

Using the MCP Tools

AutoSpectra provides a wide range of automation tools that can be used through the MCP protocol:

Browser Automation

// Navigate to a URL with visible browser
await use_mcp_tool({
  server_name: "autospectra",
  tool_name: "navigate",
  arguments: {
    url: "https://example.com",
    visible: true
  }
});

// Click on an element with selector
await use_mcp_tool({
  server_name: "autospectra",
  tool_name: "click",
  arguments: {
    selector: "#login-button"
  }
});

API Testing

// Make an HTTP request
await use_mcp_tool({
  server_name: "autospectra",
  tool_name: "api_request",
  arguments: {
    method: "GET",
    url: "https://api.example.com/users/1",
    headers: {
      "Accept": "application/json"
    }
  }
});

// Validate an API response against a schema
await use_mcp_tool({
  server_name: "autospectra",
  tool_name: "validate_schema",
  arguments: {
    response: responseData,
    schema: {
      type: "object",
      required: ["id", "name", "email"],
      properties: {
        id: { type: "number" },
        name: { type: "string" },
        email: { type: "string", format: "email" }
      }
    }
  }
});

Interactive Debugging

// Create a debug test session
await use_mcp_tool({
  server_name: "autospectra",
  tool_name: "debug_test",
  arguments: {
    testName: "login-flow",
    testScript: `
      step('step1', 'navigate', { url: 'https://example.com/login' });
      step('step2', 'type', { selector: '#username', text: 'testuser' });
      step('step3', 'click', { selector: '#login-button' });
    `,
    breakAt: ['step3'],
    runImmediately: true
  }
});

For complete documentation of all available tools and their parameters, see:

Documentation

AutoSpectra provides comprehensive documentation of its tooling capabilities:

Tools Documentation Index - Overview and index of all tools documentation
Current Tools List - Complete reference of all currently available tools with parameters and examples
Future Tool Enhancements - Roadmap of planned enhancements and missing tools

Project Structure

autospectra-mcp-server/
├── docs/                # Documentation
│   ├── guides/          # User and developer guides
│   ├── api/             # API documentation
│   └── examples/        # Example usage
├── scripts/             # Utility and helper scripts
├── src/                 # Source code
│   ├── automation/      # Browser automation
│   ├── computerUse/     # Claude computer use integration
│   ├── frameworks/      # Test framework integration
│   ├── nlp/             # NLP functionality
│   ├── server/          # Server-specific code
│   └── utils/           # Utilities
├── tests/               # Test files
│   ├── integration/     # Integration tests
│   ├── unit/            # Unit tests
│   └── e2e/             # End-to-end tests

Integration with AI Agents

AutoSpectra seamlessly integrates with any AI agent supporting the MCP protocol:

Universal Compatibility: Works with Claude, ChatGPT, Gemini, Perplexity, and more
Advanced Capabilities: Access specialized features like Claude's Computer Use
Flexible Workflows: Combine local and cloud-based automation

See the AI Integration Guide for more information.

Platform Integrations

AutoSpectra works with various AI platforms and development environments:

Claude Desktop/Cloud: Enhanced automation with Computer Use capabilities
VS Code Extensions: Seamless integration with development workflows
ChatGPT & OpenAI: Full support for GPT-based assistants
Gemini & Other Models: Compatible with all major AI platforms

See the Platform Integration Guide for more information.

Docker Support

# Build the Docker image
npm run docker:build

# Run with Docker
npm run docker:run

Testing

# Run all tests
npm run test:all

# Run specific tests
npm run test:accessibility
npm run test:computer-use
npm run test:e2e

Contributing

Contributions are welcome! Please see CONTRIBUTING.md for more information.

License

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