How do I install Mcp Multi Model?

Add the server to your MCP config with `"command": "npx", "args": ["-y", "mcp-multi-model"]` and set your API keys in the `env` block. Alternatively, clone the repo and run `npm install && npm run setup` for an interactive wizard.

Yes, for cloud models you need the corresponding API keys (e.g., `DEEPSEEK_API_KEY`, `GEMINI_API_KEY`). Local models (Ollama, LM Studio, etc.) require no API key and run entirely on your machine.

What credentials does it need?

It reads `DEEPSEEK_API_KEY`, `GEMINI_API_KEY`, `OPENAI_API_KEY` from the environment. Store these in your client's env block or a secrets manager — never commit them to a repository — and grant the narrowest scope that still covers your use case.

SSyncDev

Start a project

MCP Multi Model MCP Server

MCP server for Claude Code — parallel multi-model queries, smart routing, image/video gen across OpenAI (GPT-5, GPT Image), Gemini (Imagen 4, Veo)

Local serverstdioGo

What is the MCP Multi Model MCP Server?

MCP server for Claude Code — parallel multi-model queries, smart routing, image/video gen across OpenAI (GPT-5, GPT Image), Gemini (Imagen 4, Veo), DeepSeek, Kimi &

What it actually does

One MCP server. All the models you need. Zero tab-switching.

More MCP options

Compare MCP servers by category, or browse hosted MCP servers if you prefer an endpoint over a local process.

Maintainer setup documentation.

Recorded tools

Check the linked publisher documentation and your connected client's tool list. Names and availability can vary with the server version and account permissions.

Tool	What it does
ask_ai	Query any model — unified entry with temperature / top_p control
ask_deepseek	Query DeepSeek directly
ask_gemini	Query Gemini directly
ask_kimi	Query Kimi directly
ask_all	Query all models in parallel, compare results
ask_both	Query any two models in parallel
delegate	Smart routing — auto-picks the best model for the task
generate_image	Text → image via Gemini Imagen
generate_video	Text → video via Gemini Veo
translate	CN ↔ EN translation
research	Deep research with web search
check_health	Ping all models, report status and latency
imagen-4-fast	:predict
imagen-4-ultra	:predict

How to install the MCP Multi Model MCP Server

{
  "mcpServers": {
    "multi-model": {
      "command": "npx",
      "args": ["-y", "mcp-multi-model"],
      "env": {
        "DEEPSEEK_API_KEY": "sk-...",
        "GEMINI_API_KEY": "AI..."
      }
    }
  }
}

Configuration as documented by the project. Restart the client after saving.

Configuration

Variable	Description	Required
DEEPSEEK_API_KEY	Credential the server authenticates with.	Yes
GEMINI_API_KEY	Credential the server authenticates with.	Yes
OPENAI_API_KEY	Credential the server authenticates with.	Yes

Example prompts to try

“Use MCP Multi Model to ask ai.”
“Use MCP Multi Model to ask deepseek.”
“Use MCP Multi Model to ask gemini.”

Frequently asked questions

12+ providers are preconfigured, including OpenAI, Gemini, DeepSeek, Kimi, Grok, Perplexity, Anthropic (via OpenRouter), Mistral, Groq, Qwen, GLM, Together, and local runners (Ollama, LM Studio, llama.cpp, vLLM). Models without an API key are skipped automatically.