GPT MCP Proxy

by wricardo

API/Gateways & Proxies REST API Proxy GPT Actions HTTP

A REST API server that provides HTTP access to Multiple Command Protocol (MCP) tools. This server acts as a bridge between HTTP clients and MCP-compliant tool servers, allowing tools to be discovered and executed via REST endpoints.

View on GitHub

Last updated: N/A

What is GPT MCP Proxy?

GPT MCP Proxy is a REST API server that acts as a bridge between HTTP clients and MCP-compliant tool servers. It allows you to discover and execute MCP tools via REST endpoints, making it useful for integrating MCP tools with custom GPT through Actions.

How to use GPT MCP Proxy?

Set up environment variables (NGROK_AUTH_TOKEN, NGROK_DOMAIN, MCP_CONFIG_FILE). 2. Prepare an mcp_settings.json configuration file with your MCP server configurations. 3. Run the server using go run main.go. You can then access the API endpoints to list servers, get tool details, and execute tools.

Key features of GPT MCP Proxy

List available MCP servers and their tools
Get detailed information about specific tools
Execute tools with custom parameters
OpenAPI 3.1.0 specification
Automatic public HTTPS exposure via ngrok

Use cases of GPT MCP Proxy

Integrating MCP tools with custom GPT through Actions
Providing a RESTful interface to MCP tools for easier access
Automating the execution of MCP tools
Building custom applications that interact with MCP tools

FAQ from GPT MCP Proxy

What is MCP?

MCP stands for Multiple Command Protocol. It's a protocol for interacting with tools.

What is ngrok used for?

ngrok is used to expose the server to the internet via a public HTTPS URL.

What environment variables are required?

The required environment variables are NGROK_AUTH_TOKEN, NGROK_DOMAIN, and optionally MCP_CONFIG_FILE.

How do I configure the MCP servers?

You configure the MCP servers in the mcp_settings.json file.

How do I execute a tool?

You can execute a tool by sending a POST request to the /mcp/{serverName}/tools/{toolName}/execute endpoint.