Model Hub MCP
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Model Hub MCP list all available models from OpenAI"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
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
Related MCP server: Outsource MCP
Quick Start (npx)
# Run with environment variables
OPENAI_API_KEY=your_key npx @akiojin/model-hub-mcpNote: The package will be downloaded from npm on first run.
Installation
Global Installation
npm install -g @akiojin/model-hub-mcpLocal Installation
npm install @akiojin/model-hub-mcpConfiguration
Copy
.env.exampleto.env:
cp .env.example .envSet API keys for each provider in the
.envfile:
OPENAI_API_KEY=your_openai_api_key_here
ANTHROPIC_API_KEY=your_anthropic_api_key_here
GOOGLE_API_KEY=your_google_api_key_hereNote: You can leave API keys empty for providers you don't plan to use.
Build
Compile TypeScript code:
npm run buildUsage
This MCP server is not meant to be run directly. It should be configured in your MCP client configuration.
See the "MCP Client Configuration Examples" section below for setup instructions.
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
Claude Code
You can easily add this MCP server to Claude Code using the following command:
claude mcp add model-hub -s user \
-e GOOGLE_API_KEY=$GEMINI_API_KEY \
-e OPENAI_API_KEY=$OPENAI_API_KEY \
-e ANTHROPIC_API_KEY=$ANTHROPIC_API_KEY \
-- npx -y @akiojin/model-hub-mcpThis command assumes you have environment variables set in your shell:
$GEMINI_API_KEY- Your Google AI API key$OPENAI_API_KEY- Your OpenAI API key$ANTHROPIC_API_KEY- Your Anthropic API key
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"
}
}
}
}License
MIT
Available Tools
3 toolsget_modelC
Get details of a specific model from a provider
Inputs: provider (required), model_id (required).
list_all_modelsB
List all available models from all configured providers
Inputs: no named parameters.
list_modelsC
List all available models from a specific provider
Inputs: provider (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 3 tools
The tools 'list_all_models' and 'list_models' have overlapping purposes that could cause confusion, as both involve listing models with only a subtle distinction (all providers vs. specific provider). The 'get_model' tool is distinct, but the ambiguity between the two listing tools is significant enough to risk misselection by an agent.
All tool names follow a consistent verb_noun pattern (get_model, list_all_models, list_models), using snake_case throughout. The naming is predictable and readable, with no deviations in style or convention.
With only 3 tools, the server feels thin for a 'Model Hub' domain, which might involve more operations like uploading, updating, or deleting models. While the count is not extreme, it borders on being under-scoped for the apparent purpose.
The tool surface is significantly incomplete for a model hub domain. There are no tools for creating, updating, or deleting models, and no operations for managing providers or configurations. This leaves obvious gaps that could cause agent failures in common workflows.
Maintenance
Related MCP Connectors
MCP server for OpenAI API (chat completions, image generation, embeddings) via AceDataCloud
An MCP server that integrates with Discord to provide AI-powered features.
MCP server for AI dialogue using various LLM models via AceDataCloud
MCP server unifying ERPs, CRMs, APIs and knowledge base for Claude, ChatGPT and Gemini.
Related MCP Servers
- FlicenseBqualityDmaintenanceA lightweight MCP server that provides a unified interface to various LLM providers including OpenAI, Anthropic, Google Gemini, Groq, DeepSeek, and Ollama.6736-
- AlicenseAqualityDmaintenanceAn MCP server that enables AI applications to access 20+ model providers (including OpenAI, Anthropic, Google) through a unified interface for text and image generation.230MIT
- FlicenseAqualityDmaintenanceAn MCP server for discovering and querying over 300 AI models available on OpenRouter. It enables users to list, search, filter, compare, and get detailed information about models with pricing, context limits, and capabilities.51-
- AlicenseAqualityFmaintenanceMCP server that provides AI assistants with real-time, current information about AI models from OpenAI, Anthropic, and Google, including pricing, capabilities, and context windows.453 PyPIMIT