Universal MCP Tool

Provides a configurable MCP server to convert Web APIs into MCP endpoints with testing and API key management.

python

69

GitHub Stars

python

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "suhuail-api-mcp": {
      "command": "python",
      "args": [
        "启动_universal_mcp.py"
      ]
    }
  }
}

You can turn Web API interfaces into a configurable MCP tool that AI assistants use, enabling easy API access, testing, and key management without exposing secrets. This MCP server lets you manage multiple APIs, test them, and run them locally or integrate with an AI workflow.

How to use

You start the MCP server on your machine and run it from your command line. Use a client that supports MCP to connect to the local server endpoint you configured. The tool lets you add APIs, specify how requests are sent (GET or POST), provide a description, manage API keys, and test the API right from the management UI. You can then make requests through the MCP interface or have your AI assistant call registered APIs without handling keys directly.

Key features you’ll use regularly:

API management: add, edit, and remove API configurations
API tests: validate requests and responses and ensure formats match expectations
API key management: choose where keys are sent (header, query, or body) and which key name to use
Start service: run the MCP server and keep it running for AI integration