Multi Model Advisor

What is Multi Model Advisor about?

Multi Model Advisor lets a user pose a single query and receive blended insights from several locally hosted Ollama models, each acting with a distinct persona. The server gathers each model's response and returns the collection so Claude (or any MCP‑compatible client) can produce a unified answer.

How to use Multi Model Advisor?

1. Install – either via Smithery:

   npx -y @smithery/cli install @YuChenSSR/multi-ai-advisor-mcp --client claude
   

   or manually clone, run npm install, and npm run build.
2. Configure – create a .env file with Ollama URL, default model list, and system prompts for each model.
3. Connect to Claude – add an entry to claude_desktop_config.json pointing to the built index.js (or use the npx‑based command in the serverConfig below).
4. Ask a question – in Claude, reference the advisor, e.g.:

   what are the most important skills for success in today's job market, you can use gemma3:1b, llama3.2:1b, deepseek-r1:1.5b to help you
   

   Claude will invoke the query-models tool, the server contacts the three models, and Claude synthesizes the replies.

Key features of Multi Model Advisor

• Simultaneous querying of multiple Ollama models with a single prompt.
• Persona‑based system prompts for each model (creative, empathetic, analytical).
• list-available-models tool to inspect installed Ollama models.
• Environment‑variable driven configuration (server name, debug flag, default models, custom prompts).
• Seamless integration with Claude for Desktop.
• Simple installation via Smithery or standard npm workflow.

Use cases of Multi Model Advisor

• Decision support – gather diverse technical, ethical, and business viewpoints before choosing a strategy.
• Creative brainstorming – combine imaginative and logical suggestions for product ideas.
• Learning assistance – receive explanations from a “teacher” model, a “coach” model, and an “analyst” model.
• Risk assessment – let analytical models articulate step‑by‑step reasoning while empathetic models highlight human impact.

FAQ from the Multi Model Advisor

Q: Do I need an internet connection? A: No. All models run locally via Ollama; only the local Ollama API endpoint is required.

Q: Which models can I use? A: Any model installed in Ollama. The default set includes gemma3:1b, llama3.2:1b, and deepseek-r1:1.5b, but you can modify DEFAULT_MODELS in .env.

Q: How do I change a model’s persona? A: Edit the corresponding <MODEL>_SYSTEM_PROMPT variable in .env and restart the server.

Q: What if a model fails to respond? A: The server returns the responses it received; missing models are omitted, and Claude will synthesize from the available data.

Q: Can I add more than three models? A: Yes. List any number of model names in DEFAULT_MODELS (comma‑separated) and provide matching system prompts.

Q: How do I troubleshoot Ollama connection issues? A: Verify Ollama is running (ollama serve), confirm OLLAMA_API_URL points to the correct host/port, and test the endpoint in a browser.

Q: Is there a memory limit? A: Larger models consume more RAM. If you encounter out‑of‑memory errors, switch to smaller models or increase system memory.

Multi-Model Advisor

(锵锵四人行)

A Model Context Protocol (MCP) server that queries multiple Ollama models and combines their responses, providing diverse AI perspectives on a single question. This creates a "council of advisors" approach where Claude can synthesize multiple viewpoints alongside its own to provide more comprehensive answers.

Features

• Query multiple Ollama models with a single question
• Assign different roles/personas to each model
• View all available Ollama models on your system
• Customize system prompts for each model
• Configure via environment variables
• Integrate seamlessly with Claude for Desktop

Prerequisites

• Node.js 16.x or higher
• Ollama installed and running (see Ollama installation)
• Claude for Desktop (for the complete advisory experience)

Installation

Installing via Smithery

To install multi-ai-advisor-mcp for Claude Desktop automatically via Smithery:

npx -y @smithery/cli install @YuChenSSR/multi-ai-advisor-mcp --client claude

Manual Installation

1. Clone this repository:

   git clone https://github.com/YuChenSSR/multi-ai-advisor-mcp.git 
   cd multi-ai-advisor-mcp
   

2. Install dependencies:

   npm install
   

3. Build the project:

   npm run build
   

4. Install required Ollama models:

   ollama pull gemma3:1b
   ollama pull llama3.2:1b
   ollama pull deepseek-r1:1.5b
   

Configuration

Create a .env file in the project root with your desired configuration:

# Server configuration
SERVER_NAME=multi-model-advisor
SERVER_VERSION=1.0.0
DEBUG=true

# Ollama configuration
OLLAMA_API_URL=http://localhost:11434
DEFAULT_MODELS=gemma3:1b,llama3.2:1b,deepseek-r1:1.5b

# System prompts for each model
GEMMA_SYSTEM_PROMPT=You are a creative and innovative AI assistant. Think outside the box and offer novel perspectives.
LLAMA_SYSTEM_PROMPT=You are a supportive and empathetic AI assistant focused on human well-being. Provide considerate and balanced advice.
DEEPSEEK_SYSTEM_PROMPT=You are a logical and analytical AI assistant. Think step-by-step and explain your reasoning clearly.

Connect to Claude for Desktop

1. Locate your Claude for Desktop configuration file:

   • MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json
   • Windows: %APPDATA%\Claude\claude_desktop_config.json

2. Edit the file to add the Multi-Model Advisor MCP server:

{
  "mcpServers": {
    "multi-model-advisor": {
      "command": "node",
      "args": ["/absolute/path/to/multi-ai-advisor-mcp/build/index.js"]
    }
  }
}

3. Replace /absolute/path/to/ with the actual path to your project directory

4. Restart Claude for Desktop

Usage

Once connected to Claude for Desktop, you can use the Multi-Model Advisor in several ways:

List Available Models

You can see all available models on your system:

Show me which Ollama models are available on my system

This will display all installed Ollama models and indicate which ones are configured as defaults.

Basic Usage

Simply ask Claude to use the multi-model advisor:

what are the most important skills for success in today's job market, 
you can use gemma3:1b, llama3.2:1b, deepseek-r1:1.5b to help you 

Claude will query all default models and provide a synthesized response based on their different perspectives.

How It Works

1. The MCP server exposes two tools:

   • list-available-models: Shows all Ollama models on your system
   • query-models: Queries multiple models with a question

2. When you ask Claude a question referring to the multi-model advisor:

   • Claude decides to use the query-models tool
   • The server sends your question to multiple Ollama models
   • Each model responds with its perspective
   • Claude receives all responses and synthesizes a comprehensive answer

3. Each model can have a different "persona" or role assigned, encouraging diverse perspectives.

Troubleshooting

Ollama Connection Issues

If the server can't connect to Ollama:

• Ensure Ollama is running (ollama serve)
• Check that the OLLAMA_API_URL is correct in your .env file
• Try accessing http://localhost:11434 in your browser to verify Ollama is responding

Model Not Found

If a model is reported as unavailable:

• Check that you've pulled the model using ollama pull <model-name>
• Verify the exact model name using ollama list
• Use the list-available-models tool to see all available models

Claude Not Showing MCP Tools

If the tools don't appear in Claude:

• Ensure you've restarted Claude after updating the configuration
• Check the absolute path in claude_desktop_config.json is correct
• Look at Claude's logs for error messages

RAM is not enough

Some managers' AI models may have chosen larger models, but there is not enough memory to run them. You can try specifying a smaller model (see the Basic Usage) or upgrading the memory.

License

MIT License

For more details, please see the LICENSE file in this project repository

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.