Meta API

You can run a Meta API MCP Server to connect multiple APIs to large language models through the Model Context Protocol (MCP). This enables AI assistants to access real-world data from HTTP APIs via simple, configurable endpoints and tools.

How to use

You will run the MCP server as a local or remote process and connect your MCP client to it. Start the server with a configuration that defines one or more API endpoints, authentication methods, and how to transform HTTP calls into MCP tools. You can load configurations from local files or remote URLs, and you can convert existing Postman collections into MCP-compatible configurations to quickly expose endpoints to your AI assistants.

How to install

# Global installation (recommended)
npm install -g meta-api-mcp-server

# Install from source
git clone https://github.com/savhascelik/meta-api-mcp-server.git
cd meta-api-mcp-server
npm install

Additional sections

Configuration and usage examples in this guide illustrate practical, ready-to-run setups. You can start from a minimal config and extend it to load multiple APIs, switch authentication methods, or point to remote configuration lists.

Usage patterns you can employ include loading a default configuration or pointing to a specific file or remote URL. You can also run the server with a Postman collection to automatically generate MCP tools for each endpoint.

Postman collection conversion lets you export a collection and start the server with that collection file. The server analyzes endpoints, detects authentication, and creates MCP tools automatically. You can then specify which environment variable holds your API key.

Configuration examples and tools

The server supports multiple runtime configurations through simple JSON files. A typical configuration declares the API base URL, authentication, and endpoints with their HTTP methods and parameters.

{
  "apiId": "my-api",
  "handlerType": "httpApi",
  "baseUrl": "https://api.example.com",
  "authentication": {
    "type": "bearerToken",
    "envVariable": "MY_API_TOKEN"
  },
  "endpoints": [
    {
      "mcpOperationId": "getUsers",
      "description": "Get a list of users",
      "targetPath": "/users",
      "targetMethod": "GET",
      "parameters": [
        {
          "name": "page",
          "in": "query",
          "required": false,
          "type": "integer",
          "description": "Page number"
        }
      ]
    }
  ]
}

Postman collections and MCP tools

You can convert Postman collections to MCP-compatible configurations. Export a collection, then start the server with the collection file to generate MCP tools for each endpoint. You will be told which environment variable to use for your API key.

# Start with a Postman collection file
meta-mcp my-collection.postman_collection.json

Project structure and environment variables

The server is organized to keep configuration files in a dedicated folder and load them at startup. You can specify a default folder or provide a remote URL to load configurations.

Available tools

MCP API Editor

A web-based editor to create or edit JSON configuration files for MCP and to convert Postman collections into MCP-compatible configurations.

Postman Collection Converter

Converts Postman collections to MCP configurations, validating endpoints, parameters, and authentication to generate MCP tools.