Debug MCP Servers with Inspector | Manufact

Debug MCP Servers with Inspector

Open-source developer tool for testing and debugging MCP servers. Test tools, explore resources, manage prompts, and monitor connections, with support for MCP-UI and MCP Apps widgets.

Try online View docs

Trusted by developers debugging MCP servers at top companies

Live demo

Add an MCP server and test it.

Add a remote MCP server and start testing it in the Inspector right here.

Open in new tab View source

Inspector | mcp-use

v20.3.8

MCP Inspector

Inspect and debug MCP (Model Context Protocol) servers

Connected Servers

No servers connected yet. Add a server above to get started.

Connect

Copy Config

Alias

URL

Tip: You can paste a copied connection config (JSON) to auto-populate the form

Protocol Version

Auto

Authentication

Custom Headers

Configuration

Connect

Get started

Three ways to use the Inspector.

Use it online, run it locally with npx, or deploy to your own infrastructure. Same features everywhere.

Online

Open the hosted version in your browser. Connect to any MCP server with a URL. No installation needed.

inspector.manufact.com

Open Inspector

npx

Run locally with a single command. Connect to local servers during development. Full feature parity.

npx @mcp-use/inspector

View on npm

Self-hosted

Run on your own infrastructure with npx. Use --no-open for headless servers, CI, or air-gapped environments.

npx @mcp-use/inspector --no-open --port 8080

CLI guide

Features

Everything you need to debug MCP servers.

Full visibility into your MCP server during development. Test every primitive before connecting to agents.

Tool testing

List, inspect, and execute MCP tools with custom parameters. See request and response data in real time.

Resource browser

Browse and read resources exposed by your server. View metadata, test subscriptions, and inspect content.

Prompt management

View and test prompt templates with different arguments. Validate prompts before connecting to agents.

RPC logging

See every JSON-RPC message between client and server. Debug exactly what gets sent and what comes back.

Widget preview

Test MCP Apps and MCP-UI widgets directly in the Inspector. See how they render in real chat clients.

Multi-transport

Connect via stdio, SSE, or HTTP. Test your server regardless of how it communicates with clients.

Widget testing

Test MCP Apps with UI widgets.

The Inspector supports MCP Apps and MCP-UI widgets. Test interactive components, verify tool calls, and debug widget state before deploying to production.

What you can test

Widget rendering: See how your widgets look in real chat clients.
Tool calls from widgets: Test window.openai.callTool() interactions.
Display modes: Switch between inline, PiP, and fullscreen.
Widget state: Inspect and debug widgetState persistence.
Dev mode: Hot reload for rapid widget development.
Console proxy: See widget console.log output in the Inspector.

window.openai API emulation

The Inspector fully emulates the window.openai API that widgets use in ChatGPT. Your components work identically in the Inspector and in production.

// Available in widgets

window.openai.toolInput

window.openai.toolOutput

window.openai.widgetState

window.openai.theme

window.openai.callTool()

window.openai.setWidgetState()

Debugging

See every JSON-RPC message.

The RPC Logger shows all communication between the Inspector and your MCP server. Filter by method, search message content, and debug protocol issues.

Real-time logging

Messages appear as they happen. No refresh needed.

Filter and search

Filter by method type. Search message content.

Message details

Expand any message to see full request and response.

Chat

Chat with your MCP server.

The Inspector includes a chat interface that connects your MCP tools to an LLM. Test how agents will interact with your server in a real conversation.

Bring your own key (BYOK)

The Chat feature uses your own API key. Your key is stored locally in your browser and never sent to our servers. All requests go directly from your device to your LLM provider.

OpenAI, Anthropic, and other providers

Keys stored in browser localStorage

Direct API calls, no proxy

Test tool selection and execution

Try chat now Book a demo