Which integrations are available for this server?

Provides tools for launching and managing Electron applications, interacting with UI elements, executing scripts in the main process, capturing screenshots, and performing visual and accessibility testing.

How do I use electron-mcp-server?

1. Click on "Install Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@electron-mcp-server launch the electron app and click the 'Start' button" That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

electron-mcp-server

by kanishka-namdeo

Overview Schema Related Servers Score Discussions

TypeScript

Local

Electron MCP Server

A Model Context Protocol (MCP) server for testing Electron applications using Playwright. This server enables AI coding tools like Cursor and Claude Code to interact with Electron applications for automated testing and development.

Features

Electron App Lifecycle: Launch and manage Electron applications programmatically
CDP Connection: Connect to running Electron apps via Chrome DevTools Protocol with retry logic and IPv6/IPv4 fallback
Element Interaction: Click, fill, select, and interact with UI elements
Navigation: Navigate to URLs and manage page state, with CDP-backed navigation history tools
Window Management: Control Electron main windows (focus, minimize, maximize)
Main Process Access: Execute scripts in the Electron main process
Visual Testing: Capture screenshots and compare against baselines
Accessibility Testing: Retrieve accessibility tree information, structured accessibility snapshots, and role-based interactions
Session Management: Multiple concurrent test sessions with UUID tracking
Advanced CDP Features: Network emulation, geolocation override, device metrics, performance monitoring, navigation history
Code Generation: Record user flows and export Playwright tests
Robust Error Handling: Categorized errors with automatic classification and retry recommendations

Related MCP server: mcp-electron-driver

Installation

Using npm (Recommended)

npm install -g @kanishka-namdeo/electron-mcp-server

From Source

git clone https://github.com/kanishka-namdeo/electron-mcp-server.git
cd electron-mcp-server
npm install
npm run build

Usage

Running the Server

# Development mode with hot reload
npm run dev

# Production mode
npm run start

# Build TypeScript
npm run build

AI Tool Integration

Claude Desktop

Add to your Claude Desktop configuration file:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "electron-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "@kanishka-namdeo/electron-mcp-server"
      ],
      "env": {
        "LOG_LEVEL": "info",
        "NODE_ENV": "production"
      }
    }
  }
}

Or using a global installation:

{
  "mcpServers": {
    "electron-mcp-server": {
      "command": "electron-mcp-server",
      "env": {
        "LOG_LEVEL": "info",
        "NODE_ENV": "production"
      }
    }
  }
}

Cursor

Add to your Cursor MCP settings (.cursor/mcp.json):

{
  "mcpServers": {
    "electron-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "@kanishka-namdeo/electron-mcp-server"
      ]
    }
  }
}

Or for global installation:

{
  "mcpServers": {
    "electron-mcp-server": {
      "command": "electron-mcp-server"
    }
  }
}

Available Tools

The Electron MCP Server provides 44 tools across 6 categories:

App Lifecycle (4 tools)

Tool	Description
`launch_electron_app`	Launch an Electron application
`connect_to_electron_cdp`	Connect to a running Electron app via CDP
`close_session`	Close a test session
`list_sessions`	List all active sessions

Element Interaction (10 tools)

Tool	Description
`navigate`	Navigate to a URL
`click`	Click on an element
`fill`	Fill an input field with text
`select`	Select an option from a dropdown
`get_text`	Get text content of an element
`screenshot`	Take a screenshot of the page or element
`wait_for_selector`	Wait for an element to appear
`execute`	Execute JavaScript in the renderer process
`get_page_info`	Get page URL and title

Main Process & Window Control (8 tools)

Tool	Description
`execute_main_process_script`	Execute JavaScript in the main process
`get_main_window_info`	Get window information
`focus_main_window`	Focus the main window
`minimize_main_window`	Minimize the main window
`maximize_main_window`	Maximize the main window
`get_unresponsive_callstack`	Report capability info for unresponsive renderer callstack capture in Electron 34+ apps
`get_shared_dictionary_info`	Report capability info for HTTP shared dictionary compression in Electron 34+ apps
`clear_shared_dictionary_cache`	Report capability info for clearing shared dictionary cache in Electron 34+ apps

Visual Testing & Accessibility (11 tools)

Tool	Description
`take_screenshot`	Capture a screenshot
`capture_element_screenshot`	Screenshot a specific element
`compare_screenshots`	Compare against a baseline
`get_viewport_size`	Get current viewport dimensions
`set_viewport_size`	Set viewport dimensions
`get_accessibility_tree`	Retrieve accessibility tree
`get_accessibility_snapshot`	Get Playwright accessibility snapshot for the current page
`find_accessible_node`	Find nodes by accessibility role/name with optional fuzzy matching
`interact_accessible_node`	Click or fill accessible nodes by role/name

Advanced CDP Features (12 tools)

Tool	Description
`get_protocol_info`	Get CDP protocol version and browser info
`emulate_network_conditions`	Emulate slow/offline network
`reset_network_conditions`	Reset to default network settings
`set_geolocation`	Override geolocation
`clear_geolocation`	Remove geolocation override
`set_device_metrics`	Emulate mobile device
`get_console_messages`	Capture console logs
`get_performance_metrics`	Get performance metrics
`clear_browser_cache`	Clear cache and cookies
`get_user_agent`	Get current user agent
`get_navigation_history`	Get navigation history entries via CDP
`restore_navigation_history`	Restore a history entry via CDP

Codegen & Recording

Tool	Description
`start_recording`	Start recording a flow for a session
`stop_recording`	Stop recording and return structured steps
`export_recording_as_test`	Export recorded steps as a Playwright test snippet

Development

Testing

The project has a comprehensive test suite with multiple categories:

# Run all tests
npm test

# Run tests with coverage
npm run test:coverage

# Run unit tests only
npm run test:unit

# Run integration tests only
npm run test:integration

# Run E2E tests only (requires running Electron app)
npm run test:e2e

# Run compliance tests only
npm run test:compliance

# Run tests in watch mode
npm run test:watch

Linting

# Run linter
npm run lint

# Fix linting issues
npm run lint:fix

Type Checking

npm run typecheck

Building

# Build TypeScript
npm run build

# Development mode with hot reload
npm run dev

# Production mode
npm start

Project Structure

electron-mcp-server/
├── src/
│   ├── core/
│   │   ├── errors.ts              # Custom error classes
│   │   ├── errors-enhanced.ts     # Enhanced error handling with classification
│   │   ├── cdp-utils.ts           # CDP connection utilities with retry logic
│   │   ├── connection-health.ts   # Connection health monitoring
│   │   ├── logger.ts              # Pino logging setup
│   │   └── types.ts               # TypeScript type definitions
│   ├── session/
│   │   ├── session-manager.ts   # Session lifecycle management
│   │   └── index.ts
│   ├── tools/
│   │   ├── handlers/
│   │   │   ├── app-lifecycle.ts       # App launch and CDP connection
│   │   │   ├── element-interaction.ts # Click, fill, select, navigate
│   │   │   ├── main-process.ts        # Window control and main process scripts
│   │   │   ├── visual-testing.ts      # Screenshots, viewport, accessibility
│   │   │   └── cdp-advanced.ts        # Network, geolocation, device metrics
│   │   ├── tools.ts                   # Tool definitions
│   │   ├── validation.ts              # Zod schemas
│   │   ├── validation-enhanced.ts     # Enhanced validation schemas
│   │   └── index.ts
│   └── index.ts                       # Main MCP server
├── tests/
│   ├── unit/              # Unit tests
│   ├── integration/       # Integration tests
│   ├── e2e/               # End-to-end tests
│   ├── compliance/        # MCP protocol compliance tests
│   ├── utils/             # Test utilities
│   └── fixtures/          # Test fixtures
├── test-app/              # Electron test application
├── .trae/
│   └── docs/              # Phase 1 & 2 documentation
├── CHANGELOG.md           # Version history
├── LICENSE                # MIT License
├── package.json
├── tsconfig.json
└── vitest.config.ts

Environment Variables

LOG_LEVEL: Logging level (default: info)
NODE_ENV: Environment (default: production)

License

MIT

This server cannot be installed

license - permissive license

quality - not tested

maintenance

How are these scores calculated?

Maintenance

–Maintainers

–Response time

–Release cycle

–Releases (12mo)

Commit activity

Resources

Need Help?

Related Servers

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Latest Blog Posts

Your AI Chatbot Just Exposed Your CEO's Salary to an Intern
By Om-Shree-0709 on July 2, 2026.
Agent Identity
MCP Security
OAuth Delegation
Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)
By Om-Shree-0709 on June 30, 2026.
Agentic Ai
Prompt Injection
WebAssembly
Lightport: Open-Sourcing Glama's AI Gateway
By punkpeye on April 27, 2026.
OpenAI
open source

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/kanishka-namdeo/electron-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server