Model Hub MCP

model-hub-mcp

An MCP (Model Context Protocol) server that fetches AI model information from OpenAI, Anthropic, and Google.

Features

Multi-provider Support: Supports three providers - OpenAI, Anthropic, and Google AI
List Models: Retrieve a list of available models from each provider
Get Model Details: Fetch detailed information about specific models
Unified Retrieval: Batch fetch model information from all configured providers

Quick Start (npx)

# Run with environment variables
OPENAI_API_KEY=your_key npx @akiojin/model-hub-mcp

Note: The package will be downloaded from npm on first run.

Installation

Global Installation

npm install -g @akiojin/model-hub-mcp

Local Installation

npm install @akiojin/model-hub-mcp

Configuration

Copy .env.example to .env:

cp .env.example .env

Set API keys for each provider in the .env file:

OPENAI_API_KEY=your_openai_api_key_here
ANTHROPIC_API_KEY=your_anthropic_api_key_here
GOOGLE_API_KEY=your_google_api_key_here

Note: You can leave API keys empty for providers you don't plan to use.

Build

Compile TypeScript code:

npm run build

Usage

Start as MCP server:

npm start

Development mode (run TypeScript directly):

npm run dev

Available Tools

list_models

Retrieve a list of available models from a specific provider.

Parameters:

provider: "openai" | "anthropic" | "google"

get_model

Fetch detailed information about a specific model.

Parameters:

provider: "openai" | "anthropic" | "google"
model_id: Model ID (e.g., "gpt-4", "claude-3-opus", "gemini-pro")

list_all_models

Batch fetch model information from all configured providers.

MCP Client Configuration Examples

Using npx

{
  "mcpServers": {
    "model-hub": {
      "command": "npx",
      "args": ["@akiojin/model-hub-mcp"],
      "env": {
        "OPENAI_API_KEY": "your_openai_api_key",
        "ANTHROPIC_API_KEY": "your_anthropic_api_key",
        "GOOGLE_API_KEY": "your_google_api_key"
      }
    }
  }
}

After Global Installation

{
  "mcpServers": {
    "model-hub": {
      "command": "model-hub-mcp",
      "env": {
        "OPENAI_API_KEY": "your_openai_api_key",
        "ANTHROPIC_API_KEY": "your_anthropic_api_key",
        "GOOGLE_API_KEY": "your_google_api_key"
      }
    }
  }
}

After Local Installation

{
  "mcpServers": {
    "model-hub": {
      "command": "node",
      "args": ["node_modules/@akiojin/model-hub-mcp/dist/index.js"],
      "env": {
        "OPENAI_API_KEY": "your_openai_api_key",
        "ANTHROPIC_API_KEY": "your_anthropic_api_key",
        "GOOGLE_API_KEY": "your_google_api_key"
      }
    }
  }
}

License

MIT

This server cannot be installed

security - not tested

license - permissive license

quality - not tested

How are these scores calculated?

An MCP server that retrieves and provides AI model information from OpenAI, Anthropic, and Google through a unified interface.

Related MCP Servers

MCP OpenAI Server
mzxrai
-
security
A
license
-
quality
A Model Context Protocol (MCP) server that lets you seamlessly use OpenAI's models right from Claude.
Last updated -
1
24
28
JavaScript
MIT License
MCP Simple OpenAI Assistant
andybrandt
-
security
A
license
-
quality
A simple MCP server for interacting with OpenAI assistants. This server allows other tools (like Claude Desktop) to create and interact with OpenAI assistants through the Model Context Protocol.
Last updated -
31
Python
MIT License
Deep Thinking Assistant
shark-bot-0118
-
security
F
license
-
quality
An OpenAI API-based MCP server that provides deep thinking and analysis capabilities, integrating with AI editor models to deliver comprehensive insights and practical solutions.
Last updated -
OpenAI and Claude MCP
Spysailor
-
security
-
license
-
quality
A simple server that acts as a Master Control Program (MCP) for unified interaction with OpenAI and Anthropic (Claude) AI models through a single API endpoint.
Last updated -

View all related MCP servers