Install
$ agentstack add mcp-laststance-electron-mcp-server ✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ● Network access Used
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ● Environment & secrets Used
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
About
Electron MCP Server
[](https://github.com/laststance/electron-mcp-server/blob/master/LICENSE) [](https://www.npmjs.com/package/@laststance/electron-mcp-server) [](https://modelcontextprotocol.io)
A powerful Model Context Protocol (MCP) server that provides comprehensive Electron application automation, debugging, and observability capabilities. Supercharge your Electron development workflow with AI-powered automation through Chrome DevTools Protocol integration.
> ⚠️ Breaking change in v2.0 — the single send_command_to_electron tool has been split into ~40 individual electron_* tools (e.g. electron_click_by_selector, electron_fill_input). This dramatically improves LLM tool selection accuracy. Read [MIGRATION.md](./MIGRATION.md) for the full v1 → v2 mapping. v1.x stays available via npm install @laststance/electron-mcp-server@^1.7.
Demo
See the Electron MCP Server in action:
[](https://vimeo.com/1104937830)
Watch how easy it is to automate Electron applications with AI-powered MCP commands.
🎯 What Makes This Special
Transform your Electron development experience with AI-powered automation:
- 🔄 Real-time UI Automation: Click buttons, fill forms, and interact with any Electron app programmatically
- 📸 Visual Debugging: Take screenshots and capture application state without interrupting development
- 🔍 Deep Inspection: Extract DOM elements, application data, and performance metrics in real-time
- ⚡ DevTools Protocol Integration: Universal compatibility with any Electron app - no modifications required
- 🚀 Development Observability: Monitor logs, system info, and application behavior seamlessly
🔒 Security & Configuration
Configurable security levels to balance safety with functionality:
Security Levels
- 🔒 STRICT: Maximum security for production environments
- ⚖️ BALANCED: Default security with safe UI interactions (recommended)
- 🔓 PERMISSIVE: More functionality for trusted environments
- 🛠️ DEVELOPMENT: Minimal restrictions for development/testing
Environment Configuration
Configure the security level and other settings through your MCP client configuration:
VS Code MCP Settings:
{
"mcp": {
"servers": {
"electron": {
"command": "npx",
"args": ["-y", "@laststance/electron-mcp-server@latest"],
"env": {
"SECURITY_LEVEL": "balanced",
"SCREENSHOT_ENCRYPTION_KEY":"your-32-byte-hex-string"
}
}
}
}
}
Claude Desktop Configuration:
{
"mcpServers": {
"electron": {
"command": "npx",
"args": ["-y", "@laststance/electron-mcp-server@latest"],
"env": {
"SECURITY_LEVEL": "balanced",
"SCREENSHOT_ENCRYPTION_KEY":"your-32-byte-hex-string"
}
}
}
}
Alternative: Local .env file (for development):
# Create .env file in your project directory
SECURITY_LEVEL=balanced
SCREENSHOT_ENCRYPTION_KEY=your-32-byte-hex-string
Security Level Behaviors:
| Level | UI Interactions | DOM Queries | Property Access | Assignments | Function Calls | Risk Threshold | |-------|-----------------|-------------|-----------------|-------------|----------------|----------------| | strict | ❌ Blocked | ❌ Blocked | ✅ Allowed | ❌ Blocked | ❌ None allowed | Low | | balanced | ✅ Allowed | ✅ Allowed | ✅ Allowed | ❌ Blocked | ✅ Safe UI functions | Medium | | permissive | ✅ Allowed | ✅ Allowed | ✅ Allowed | ✅ Allowed | ✅ Extended UI functions | High | | development | ✅ Allowed | ✅ Allowed | ✅ Allowed | ✅ Allowed | ✅ All functions | Critical |
Environment Setup:
- Copy
.env.exampleto.env - Set
SECURITY_LEVELto your desired level - Configure other security settings as needed
cp .env.example .env
# Edit .env and set SECURITY_LEVEL=balanced
Secure UI Interaction Commands
Instead of raw JavaScript eval, use these secure commands:
// ✅ Secure button clicking
{
"command": "click_by_text",
"args": { "text": "Create New Encyclopedia" }
}
// ✅ Secure element selection
{
"command": "click_by_selector",
"args": { "selector": "button[title='Create']" }
}
// ✅ Secure keyboard shortcuts
{
"command": "send_keyboard_shortcut",
"args": { "text": "Ctrl+N" }
}
// ✅ Secure navigation
{
"command": "navigate_to_hash",
"args": { "text": "create" }
}
See [SECURITYCONFIG.md](./SECURITYCONFIG.md) for detailed security documentation.
🎯 Proper MCP Usage Guide
⚠️ Critical: Argument Structure
> Heads up — v1 docs from here onward. The sections below (argument > structure, send_command_to_electron tool reference, and the long form of > the v1 examples) describe the v1 API. v2.0 splits that single tool into > ~40 individual electron_* tools. If you are on v2, jump straight to > [MIGRATION.md](./MIGRATION.md) — the v2 tools take their arguments > top-level, so the structure pitfall described here no longer applies.
The most common mistake when using this MCP server is incorrect argument structure for the send_command_to_electron tool.
❌ Wrong (causes "selector is empty" errors):
{
"command": "click_by_selector",
"args": "button.submit-btn" // ❌ Raw string - WRONG!
}
✅ Correct:
{
"command": "click_by_selector",
"args": {
"selector": "button.submit-btn" // ✅ Object with selector property
}
}
📋 Command Argument Reference
| Command | Required Args | Example | | --------------------------------------- | ----------------------------------------------------------------------------------- | ------------------------------------------------ | | click_by_selector | {"selector": "css-selector"} | {"selector": "button.primary"} | | click_by_text | {"text": "button text"} | {"text": "Submit"} | | fill_input | {"value": "text", "selector": "..."} or {"value": "text", "placeholder": "..."} | {"placeholder": "Enter name", "value": "John"} | | send_keyboard_shortcut | {"text": "key combination"} | {"text": "Ctrl+N"} | | eval | {"code": "javascript"} | {"code": "document.title"} | | get_title, get_url, get_body_text | No args needed | {} or omit args |
🔄 Recommended Workflow
- Inspect: Start with
get_page_structureordebug_elements - Target: Use specific selectors or text-based targeting
- Interact: Use the appropriate command with correct argument structure
- Verify: Take screenshots or check page state
// Step 1: Understand the page
{
"command": "get_page_structure"
}
// Step 2: Click button using text (most reliable)
{
"command": "click_by_text",
"args": {
"text": "Create New Encyclopedia"
}
}
// Step 3: Fill form field
{
"command": "fill_input",
"args": {
"placeholder": "Enter encyclopedia name",
"value": "AI and Machine Learning"
}
}
// Step 4: Submit with selector
{
"command": "click_by_selector",
"args": {
"selector": "button[type='submit']"
}
}
🐛 Troubleshooting Common Issues
| Error | Cause | Solution | | -------------------------------- | -------------------------------- | ------------------------------ | | "The provided selector is empty" | Passing string instead of object | Use {"selector": "..."} | | "Element not found" | Wrong selector | Use get_page_structure first | | "Command blocked" | Security restriction | Check security level settings | | "Click prevented - too soon after previous click" | Same target clicked within ~1s (click_by_selector) / ~2s (click_by_text) — intentional React anti-double-submit debounce | Serialize calls (await each) or pass a different selector / text | | Cmd+A / Cmd+C / Cmd+V does nothing in electron_press_key | macOS OS-level text-editing shortcuts are bypassed by CDP Input.dispatchKeyEvent (synthetic events only — same constraint as Playwright) | Use electron_eval with el.select() / el.setSelectionRange(...) / navigator.clipboard.*; for app-level hotkeys use electron_send_keyboard_shortcut |
🛠️ Security Features
Enterprise-grade security built for safe AI-powered automation:
- 🔒 Sandboxed Execution: All code runs in isolated environments with strict resource limits
- 🔍 Input Validation: Advanced static analysis detects and blocks dangerous code patterns
- 📝 Comprehensive Auditing: Encrypted logs track all operations with full traceability
- 🖼️ Secure Screenshots: Encrypted screenshot data with clear user notifications
- ⚠️ Risk Assessment: Automatic threat detection with configurable security thresholds
- 🚫 Zero Trust: Dangerous functions like
eval, file system access, and network requests are blocked by default
> Safety First: Every command is analyzed, validated, and executed in a secure sandbox before reaching your application.
�🚀 Key Features
🎮 Application Control & Automation
- Launch & Manage: Start, stop, and monitor Electron applications with full lifecycle control
- Interactive Automation: Execute JavaScript code directly in running applications via WebSocket
- UI Testing: Automate button clicks, form interactions, and user workflows
- Process Management: Track PIDs, monitor resource usage, and handle graceful shutdowns
📊 Advanced Observability
- Screenshot Capture: Non-intrusive visual snapshots using Playwright and Chrome DevTools Protocol
- Real-time Logs: Stream application logs (main process, renderer, console) with filtering
- Window Information: Get detailed window metadata, titles, URLs, and target information
- System Monitoring: Track memory usage, uptime, and performance metrics
🛠️ Development Productivity
- Universal Compatibility: Works with any Electron app without requiring code modifications
- DevTools Integration: Leverage Chrome DevTools Protocol for powerful debugging capabilities
- Build Automation: Cross-platform building for Windows, macOS, and Linux
- Environment Management: Clean environment handling and debugging port configuration
📦 Installation
VS Code Integration (Recommended)
[](https://insiders.vscode.dev/redirect/mcp/install?name=electron&config=%7B%22command%22%3A%22npx%22%2C%22args%22%3A%5B%22-y%22%2C%22electron-mcp-server%22%5D%7D)
Add to your VS Code MCP settings:
{
"mcp": {
"servers": {
"electron": {
"command": "npx",
"args": ["-y", "@laststance/electron-mcp-server@latest"],
"env": {
"SECURITY_LEVEL": "balanced",
"SCREENSHOT_ENCRYPTION_KEY": "your-32-byte-hex-string-here"
}
}
}
}
}
Claude Code (CLI)
The fastest way to add this server to Claude Code is the claude mcp add command. Options come before the server name; the -- separator marks where the spawn command begins.
Project-scoped (lives in .mcp.json, share via git):
claude mcp add electron-mcp \
--env SECURITY_LEVEL=balanced \
-- npx -y @laststance/electron-mcp-server@latest
User-scoped (available across every project on this machine):
claude mcp add --scope user electron-mcp \
--env SECURITY_LEVEL=balanced \
-- npx -y @laststance/electron-mcp-server@latest
Verify:
claude mcp list
> 💡 On Windows, prefix the spawn command with cmd /c (e.g. -- cmd /c npx -y @laststance/electron-mcp-server@latest) so the npx shim resolves correctly.
Cursor IDE Integration
Cursor IDE supports MCP servers through its configuration file. Add to your Cursor MCP settings:
Location:
- macOS/Linux:
~/.cursor/mcp_config.jsonor~/.config/cursor/mcp_config.json - Windows:
%APPDATA%\Cursor\mcp_config.json
Configuration:
{
"mcpServers": {
"electron": {
"command": "npx",
"args": ["-y", "@laststance/electron-mcp-server@latest"],
"env": {
"SECURITY_LEVEL": "balanced",
"SCREENSHOT_ENCRYPTION_KEY": "your-32-byte-hex-string-here"
}
}
}
}
Setup Steps:
- Open Cursor IDE
- Go to Settings → Features → Model Context Protocol
- Enable MCP support
- Add the configuration above to your MCP config file
- Restart Cursor IDE
Verify Installation:
# Check if MCP server is accessible
curl http://localhost:9222/json
Claude Desktop Integration
Add to ~/Library/Application Support/Claude/claude_desktop_config.json:
{
"mcpServers": {
"electron": {
"command": "npx",
"args": ["-y", "@laststance/electron-mcp-server@latest"],
"env": {
"SECURITY_LEVEL": "balanced",
"SCREENSHOT_ENCRYPTION_KEY": "your-32-byte-hex-string-here"
}
}
}
}
OpenAI Codex CLI
The Codex CLI registers MCP servers through ~/.codex/config.toml (CLI and IDE extension share the same file).
One-liner (preferred):
codex mcp add electron-mcp -- npx -y @laststance/electron-mcp-server@latest
Or edit ~/.codex/config.toml directly:
[mcp_servers.electron-mcp]
command = "npx"
args = ["-y", "@laststance/electron-mcp-server@latest"]
[mcp_servers.electron-mcp.env]
SECURITY_LEVEL = "balanced"
Codex launches the server automatically on session start and exposes its electron_* tools next to the built-ins.
Global Installation
npm install -g @laststance/electron-mcp-server
🔧 Available Tools
launch_electron_app
Launch an Electron application with debugging capabilities.
{
"appPath": "/path/to/electron-app",
"devMode": true, // Enables Chrome DevTools Protocol on port 9222
"args": ["--enable-logging", "--dev"]
}
Returns: Process ID and launch confirmation
get_electron_window_info
Get comprehensive window and target information via Chrome DevTools Protocol.
{
"includeChildren": true // Include child windows and DevTools instances
}
Returns:
- Window IDs, titles, URLs, and types
- DevTools Protocol target information
- Platform details and process information
take_screenshot
Capture high-quality screenshots using Playwright and Chrome DevTools Protocol.
{
"outputPath": "/path/to/screenshot.png", // Optional: defaults to temp directory
"windowTitle": "My App" // Optional: target specific window
}
Features:
- Non-intrusive capture (doesn't bring window to front)
- Works with any Electron app
- Fallback to platform-specific tools if needed
send_command_to_electron
> v1 only. Removed in v2. See [MIGRATION.md](./MIGRATION.md) for the > per-command replacement (electron_click_by_selector, electron_fill_input, > electron_eval, etc.).
Execute JavaScript commands in the running Electron application via WebSocket.
{
"command": "eval", // Built-in commands: eval, get_title, get_url, click_button, console_log
"args": {
"code": "document.querySelector('button').click(); 'Button clicked!'"
}
}
Enhanced UI Interaction Commands:
find_elements: An
…
Source & license
This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: laststance
- Source: laststance/electron-mcp-server
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet — be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.