Model Hub

Provides unified access to model metadata from OpenAI, Anthropic, and Google via MCP client integration.
  • javascript

0

GitHub Stars

javascript

Language

4 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": {
    "akiojin-model-hub-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@akiojin/model-hub-mcp"
      ],
      "env": {
        "GOOGLE_API_KEY": "YOUR_GOOGLE_API_KEY",
        "OPENAI_API_KEY": "YOUR_OPENAI_API_KEY",
        "ANTHROPIC_API_KEY": "YOUR_ANTHROPIC_API_KEY"
      }
    }
  }
}

This MCP server fetches AI model information from OpenAI, Anthropic, and Google, and presents a unified way to list models and retrieve detailed model data from all configured providers. It helps you compare, combine, and access model metadata in a consistent interface from your MCP client.

How to use

You integrate this MCP server into your MCP client configuration to access model information from multiple providers. The server exposes endpoints to list models from a chosen provider, get detailed information about a specific model, and batch-fetch models from all configured providers. Use your MCP client to request data from the server, specifying the provider and model identifiers as needed.

Typical usage flows include: listing available models for a provider (openai, anthropic, or google), retrieving detailed model data by model_id, and performing a batch fetch to collect information from all configured providers in one call.

How to install

Prerequisites you need before installing:
- Node.js (16.x or newer) and npm
- Internet access to fetch packages from npm
- A MCP client environment that can connect to MCP servers
Step-by-step commands to use the MCP server with npm and npx:
1) Quick start with npx (no local install required):
`OPENAI_API_KEY=your_key npx @akiojin/model-hub-mcp
2) Global installation (optional):
`npm install -g @akiojin/model-hub-mcp
3) Local installation (recommended if you plan to modify or host locally):
`npm install @akiojin/model-hub-mcp
4) Build (for TypeScript sources, if you clone and run locally):
`npm run build

Configuration and runtime notes

Configure API keys in a single environment file so your MCP client can securely pass credentials to the server. You can leave keys blank for providers you do not plan to use.

Key environment variables shown in examples:

  • OPENAI_API_KEY
  • ANTHROPIC_API_KEY
  • GOOGLE_API_KEY
Example runtime usage with environment variables passed at startup:
`OPENAI_API_KEY=your_openai_api_key ANTHROPIC_API_KEY=your_anthropic_api_key GOOGLE_API_KEY=your_google_api_key npx @akiojin/model-hub-mcp

Notes and tips

This MCP server is designed to be consumed by your MCP client configuration. It is not intended to run standalone in production without a client context.

Available tools

list_models

Retrieve a list of available models from a specific provider (openai, anthropic, or google).

get_model

Fetch detailed information about a specific model identified by provider and model_id.

list_all_models

Batch fetch model information from all configured providers in a single call.

Built by
VeilStrat
AI signals for GTM teams
© 2026 VeilStrat. All rights reserved.All systems operational