⚠️ This is a read-only mirror of libraries/typescript/packages/inspector in the mcp-use/mcp-use monorepo.

🚀 Please submit issues and pull requests to the monorepo instead.

🛠 This branch mirrors: canary

🌐 Source folder: libraries/typescript/packages/inspector

MCP Inspector

🔍 MCP Inspector by mcp-use is an open-source, interactive developer tool for testing and debugging MCP servers with support for MCP-UI and OpenAI Apps SDK widgets. It provides a beautiful, intuitive interface for testing tools, exploring resources, managing prompts, and monitoring server connections - all from your browser.

🚀 Try it:

• Online: inspector.mcp-use.com
• Locally: Run npx @mcp-use/inspector
• Repository: github.com/mcp-use/mcp-use

🎥 Demo

📖 Documentation

For detailed usage instructions and guides, visit docs.mcp-use.com/inspector

---

📦 Related Packages

Package	Description	Version
mcp-use	Core MCP framework
@mcp-use/cli	Build tool for MCP apps
create-mcp-use-app	Create MCP apps

---

✨ Key Features

Feature	Description
🚀 Auto-Mount	Automatically available at /inspector for all mcp-use servers
🔌 Multi-Connection	Connect to and manage multiple MCP servers simultaneously
🎯 Interactive Testing	Test tools with live execution and real-time results
📊 Real-time Status	Monitor connection states, errors, and server health
🔐 OAuth Support	Built-in OAuth flow handling with popup authentication
💾 Persistent Sessions	Connections saved to localStorage and auto-reconnect
🎨 Beautiful UI	Modern, responsive interface built with React and Tailwind
🔍 Tool Explorer	Browse and execute all available tools with schema validation
📁 Resource Browser	View and copy resource URIs with syntax highlighting
💬 Prompt Manager	Test and manage prompts with argument templates
🌐 Universal Support	Works with HTTP/SSE and WebSocket connections
🎨 Widget Support	Full support for MCP-UI and OpenAI Apps SDK widgets
🔑 BYOK Chat	Bring Your Own Key chat interface for testing conversational flows
💾 Saved Tool Calls	Save and replay tool executions for repeated testing
⌨️ Quick Actions	Cmd + K keyboard shortcuts for rapid navigation
🐳 Docker Ready	Self-host with a single Docker container for production use

---

🚀 Quick Start

Access the Inspector

There are three ways to use the MCP Inspector:

1. Online Version (Recommended for Testing)

Visit inspector.mcp-use.com - no installation required!

2. Run Locally

npx @mcp-use/inspector

Opens the inspector in your browser at http://localhost:8080

3. Auto-mounted with mcp-use Servers

When you create an MCP server with mcp-use, the inspector is automatically available at /inspector:

import { createMCPServer } from 'mcp-use/server'

const server = createMCPServer('my-server', {
  version: '1.0.0',
})

// Add your tools, resources, prompts...

server.listen(3000)
// 🎉 Inspector automatically available at http://localhost:3000/inspector

---

📖 Usage Guide

Dashboard

The main dashboard is your central hub for managing MCP server connections:

• Connected Servers Panel (left): View all your connected servers
• Connect Panel (right): Add new server connections with transport, URL, auth, and headers configuration
• Quick Actions: Access settings and clear sessions from the top bar

Adding an MCP Server

To connect to an MCP server:

1. Open Connect Panel: Click the Connect panel on the right side of the dashboard
2. Configure Transport:
   • Select "Streamable HTTP" for SSE connections
   • Select "WebSocket" for WS connections
   • Configure "stdin/stdio" for local process connections
3. Enter Server URL: Input the MCP server endpoint (e.g., https://mcp.linear.app/mcp)
4. Configure Authentication (if needed): Add OAuth credentials or API headers
5. Click Connect: Establish the connection

Example URLs:

• Linear: https://mcp.linear.app/mcp
• Local: http://localhost:3000/mcp

OAuth Authentication

For servers requiring OAuth (like Linear):

1. After clicking Connect, you'll see the authorization page
2. Click "Approve" to grant access
3. The inspector handles the redirect automatically
4. Server appears in Connected Servers list with a green indicator

Privacy Note: All authentication tokens and credentials are stored securely in your browser's local storage. Nothing is sent to our servers - everything stays on your device.

Connected Servers

Once connected, each server shows:

• Connection status indicator (green = connected)
• Server name and URL
• Available tools count
• Action buttons: Inspect, Disconnect, Remove

Click "Inspect" to open the detailed server view.

---

🔍 Server Detail View

After clicking "Inspect" on a connected server, you'll see four main tabs:

Tools Tab

The Tools tab displays all available tools from the MCP server.

Features:

• Browse all available tools with their names and descriptions
• Select a tool to view its detailed schema
• Click "Execute" to test the tool
• Enter JSON parameters in the input panel
• View real-time results with syntax highlighting
• Support for MCP-UI and OpenAI Apps SDK widgets

Example: When connected to Linear MCP server, you'll see 23+ tools for managing issues, projects, and teams.

Resources Tab

Browse available resources from the MCP server:

• View resource descriptions and metadata
• Copy resource URIs for use in your applications
• Check MIME types and resource properties
• Preview resource content

Note: Some servers (like Linear) may not expose resources, in which case you'll see "No resources available".

Prompts Tab

Test and manage pre-configured prompts:

• View all available prompts with descriptions
• Select a prompt to see its schema
• Fill in required arguments in the form
• Click "Render" to execute the prompt
• Copy the rendered output for use

Note: Not all servers provide prompts. If none are available, you'll see "No prompts available".

Chat Tab

The Chat tab provides an interactive interface to test the MCP server with an LLM using BYOK (Bring Your Own Key).

Privacy: Your API key is stored locally in your browser and never sent to our servers. All requests are made directly from your device to your LLM provider.

Setup:

1. Click "Configure API Key" to open the configuration modal
2. Select your Provider (OpenAI, Anthropic, etc.)
3. Choose the Model (gpt-4o, claude-3-5-sonnet, etc.)
4. Enter your API Key (stored locally in browser)
5. Click "Save Configuration"

Using Chat:

• Type natural language queries to test the MCP server
• View tool calls in real-time with visual indicators
• See detailed JSON output for arguments and results
• Watch the assistant's response based on tool results
• Track exactly how the MCP server processes requests

---

⌨️ Keyboard Shortcuts

Shortcut	Action
Cmd/Ctrl + K	Quick search and navigation
Esc	Close modals and overlays

Quick Search (Cmd/Ctrl + K) allows you to:

• Quickly connect to a new server
• Access documentation and tutorials
• Jump to recently used servers
• Search and execute tools directly
• Navigate to different tabs

---

💾 Persistency

The inspector automatically saves your configurations:

• Server connections persist across page reloads
• Credentials are stored securely in your browser's localStorage
• Session preferences are maintained automatically
• Clear all sessions anytime with the "Clear All" button

Your data never leaves your browser - everything is stored locally for privacy and security.

---

🐳 Self-Hosting

Deploy the MCP Inspector to your own infrastructure with a single Docker container. Perfect for enterprise environments, air-gapped networks, or when you need full control over your debugging environment.

Docker Image

The official Docker image is available on Docker Hub.

Quick Start:

docker run -d -p 8080:8080 --name mcp-inspector mcpuse/inspector:latest

Then visit http://localhost:8080 to access your self-hosted inspector.

Docker Deployment Options

Using Docker Run:

docker run -d \
  --name mcp-inspector \
  -p 8080:8080 \
  -e NODE_ENV=production \
  mcpuse/inspector:latest

Using Docker Compose:

version: '3.8'
services:
  mcp-inspector:
    image: mcpuse/inspector:latest
    ports:
      - "8080:8080"
    environment:
      - NODE_ENV=production
      - PORT=8080
    restart: unless-stopped
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:8080"]
      interval: 30s
      timeout: 10s
      retries: 3

Environment Variables

All configuration is optional. The inspector works out of the box with sensible defaults.

Variable	Default	Description
NODE_ENV	production	Node.js environment
PORT	8080	Port to run the inspector on
HOST	0.0.0.0	Host to bind to

Deploy to Railway

Deploy instantly to Railway with automatic HTTPS and custom domains:

For more deployment options and support, visit the self-hosting documentation.

---

📊 Telemetry & Privacy

The MCP Inspector collects anonymized usage data to help us improve the tool.

What Data is Collected?

We collect:

• Usage events: When you connect to servers, execute tools, read resources, or call prompts
• Anonymous user ID: A randomly generated UUID stored in your browser's localStorage
• Technical information: Package version, browser type, and connection types
• Performance data: Tool execution duration and success/failure rates

We DO NOT collect:

• Personal information (names, emails, etc.)
• Actual tool arguments or results
• Server credentials or API keys
• Resource content or data

How to Opt Out

You can disable telemetry in several ways:

Option 1: Environment Variable

# Set before starting the inspector
export MCP_USE_ANONYMIZED_TELEMETRY=false

Option 2: localStorage (Browser)

// In browser console
localStorage.setItem('mcp_inspector_telemetry_disabled', 'true')

Option 3: Package-level

// Add to your package.json
{
  "scarfSettings": {
    "enabled": false
  }
}

Telemetry Providers

We use:

• PostHog: For product analytics and feature usage tracking
• Scarf: For package download analytics and company insights

Both providers respect your privacy and follow GDPR compliance.

🤝 Contributing

We welcome contributions!

See our contributing guide for details.

---

📚 Learn More

• Inspector Documentation - Complete usage guide and tutorials
• Self-Hosting Guide - Deploy your own instance
• mcp-use Documentation - Full framework documentation
• Model Context Protocol - Official MCP specification
• GitHub Repository - Source code and examples

---

📜 License

MIT © mcp-use