MCPify

Converts API docs into an MCP server configuration and runs it for client access.

python

0

GitHub Stars

python

Language

2 months ago

First Indexed

3 weeks 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": {
    "raghav-misra-mcpify": {
      "command": "mcpify",
      "args": [
        "serve",
        "/path/to/my-api.json",
        "--auth",
        "your-token"
      ],
      "env": {
        "GEMINI_API_KEY": "your-api-key"
      }
    }
  }
}

You set up a lightweight MCP server that mirrors an API from its documentation, so an MCP client can call that API as if it were a native MCP service. By converting docs into a configured server, you get a stable interface for repeated calls, testing, and automation without manually wiring each endpoint.

How to use

You run the MCP server locally and connect your MCP client (for example, Claude or another MCP-enabled client) to it. Start from a prepared config file that describes the API, authentication, and endpoints. Then launch the server so it serves those endpoints to your client. You can also perform parsing and serving in one step to quickly bootstrap a new API integration.

Common usage patterns include:

Parse API docs into a config file, then start the server with an authentication token.
Start the server directly from a pre-generated config so the client can begin making calls immediately.
Combine both steps for a fast bootstrapping workflow and keep your config under version control for repeatability.

How to install

Prerequisites you need before installation:

Python 3.11 or newer
Gemini API key for doc parsing (required for doc-driven config generation) Install steps:
Clone the project repository
Install the package in editable mode
Prepare your environment and config file before running the server

git clone https://github.com/yourusername/mcpify.git
cd mcpify
pip install -e .

Set your Gemini API key in the environment before you parse docs, then generate a config file from the API docs and run the server using that config.

export GEMINI_API_KEY="your-api-key"

# Parse docs into a config file
mcpify parse https://api.example.com/docs -o my-api.json

# Run the server with the generated config
mcpify serve my-api.json --auth "your-api-token"

# Or do both steps in one go
mcpify quickstart https://api.example.com/docs --auth "token"

Additional notes

For desktop integration, you can point a client at the local server by providing the path to the generated config and the authentication token in the client’s configuration file.

{
  "mcpServers": {
    "my-api": {
      "command": "mcpify",
      "args": ["serve", "/path/to/my-api.json", "--auth", "your-token"]
    }
  }
}

Available tools

parse

Scrape API docs and generate a compatible MCP config file

serve

Run the MCP server from a given config and expose endpoints to MCP clients

quickstart

Parse API docs and start the server in a single step