mcpField
G
GPT MCP Proxy

GPT MCP Proxy

Local
github.com/wricardoAI & Agents8Updated 85w ago
Repository

About GPT MCP Proxy

GPT MCP Proxy is a REST API bridge for accessing tools from configured MCP servers. It is intended for HTTP clients, including custom GPT Actions, and provides endpoints for discovery, tool details, and execution.

Key features

  1. 01List configured servers and tools
  2. 02Retrieve server and tool details
  3. 03Execute tools with parameters
  4. 04Provide an OpenAPI 3.1.0 specification
  5. 05Expose the API over HTTPS via ngrok

Use cases

  1. 01Connect MCP tools to custom GPT Actions
  2. 02Discover available servers and tools over HTTP
  3. 03Run MCP tools through REST requests

MCP support

It bridges HTTP clients to MCP-compliant tool servers, exposing server and tool discovery and tool execution through REST endpoints.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

GPT MCP Proxy

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. This is very useful for integrating MCP tools with custom GPT through Actions.

Features

  • 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

Prerequisites

  • Go 1.20 or later
  • ngrok account and authtoken
  • MCP-compliant tools

Configuration

The server requires the following environment variables:

NGROK_AUTH_TOKEN=your_ngrok_auth_token
NGROK_DOMAIN=your_ngrok_domain
MCP_CONFIG_FILE=/path/to/mcp_settings.json  # Optional, defaults to mcp_settings.json
Configuration File Format

Create an mcp_settings.json file with your MCP server configurations:

{
  "mcpServers": {
    "filesystem": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-filesystem",
        "/Users/username/Desktop",
        "/path/to/other/allowed/dir"
      ]
    }
  }
}

API Endpoints

  • GET /openapi.json - OpenAPI specification
  • GET /mcp/servers - List all servers and their tools
  • GET /mcp/{serverName} - Get server details
  • GET /mcp/{serverName}/tools/{toolName} - Get tool details
  • POST /mcp/{serverName}/tools/{toolName}/execute - Execute a tool

Usage

  1. Set up environment variables
  2. Prepare configuration file
  3. Run the server:
go run main.go

Development

To build from source:

git clone https://github.com/wricardo/mcp-http-server.git
cd mcp-http-server
go build

License

MIT License

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.