1b754f52ca
* In bin/cli.js
- in the delay function, have the setTimeout return a true value.
- try the server's spawnPromise call and within the try block, use Promise.race to get the return value of the first promise to resolve. If the server is up, it will not resolve and the 2 second delay will resolve with true, telling us the server is ok. Any error will have been reported by the server startup process, so we will not pile on with more output in the catch block.
- If the server started ok, then we will await the spawnPromise call for starting the client. If the client fails to start it will report and exit, otherwise we are done and both servers are running and have reported as much. If an error is caught and it isn't SIGINT or if process.env.DEBUG is true then the error will be thrown before exiting.
* In client/bin/cli.js
- add a "listening" handler to the server, logging that the MCP inspector is up at the given port
- Add an "error" handler to the server that reports that the client port is in use if the error message includes "EADDRINUSE", otherwise throw the error so the entire contents can be seen.
* In server/src/index.ts
- add a "listening" handler to the server, logging that the Proxy server is up at the given port
- Add an "error" handler to the server that reports that the server port is in use if the error message includes "EADDRINUSE", otherwise throw the error so the entire contents can be seen.
* In package.json
- in preview script
- add --port 5173 to start the client on the proper port. This was useful in getting an instance of the client running before trying the start script. otherwise it starts on 4173
MCP Inspector
The MCP inspector is a developer tool for testing and debugging MCP servers.
Running the Inspector
From an MCP server repository
To inspect an MCP server implementation, there's no need to clone this repo. Instead, use npx. For example, if your server is built at build/index.js:
npx @modelcontextprotocol/inspector node build/index.js
You can pass both arguments and environment variables to your MCP server. Arguments are passed directly to your server, while environment variables can be set using the -e flag:
# Pass arguments only
npx @modelcontextprotocol/inspector build/index.js arg1 arg2
# Pass environment variables only
npx @modelcontextprotocol/inspector -e KEY=value -e KEY2=$VALUE2 node build/index.js
# Pass both environment variables and arguments
npx @modelcontextprotocol/inspector -e KEY=value -e KEY2=$VALUE2 node build/index.js arg1 arg2
# Use -- to separate inspector flags from server arguments
npx @modelcontextprotocol/inspector -e KEY=$VALUE -- node build/index.js -e server-flag
The inspector runs both a client UI (default port 5173) and an MCP proxy server (default port 3000). Open the client UI in your browser to use the inspector. You can customize the ports if needed:
CLIENT_PORT=8080 SERVER_PORT=9000 npx @modelcontextprotocol/inspector node build/index.js
For more details on ways to use the inspector, see the Inspector section of the MCP docs site. For help with debugging, see the Debugging guide.
Authentication
The inspector supports bearer token authentication for SSE connections. Enter your token in the UI when connecting to an MCP server, and it will be sent in the Authorization header.
Security Considerations
The MCP Inspector includes a proxy server that can run and communicate with local MCP processes. The proxy server should not be exposed to untrusted networks as it has permissions to spawn local processes and can connect to any specified MCP server.
From this repository
If you're working on the inspector itself:
Development mode:
npm run dev
Note for Windows users:
On Windows, use the following command instead:npm run dev:windows
Production mode:
npm run build
npm start
License
This project is licensed under the MIT License—see the LICENSE file for details.