Skip to content
Back to search

multi-ai-advisor-mcp

council of models for decision

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/yuchenssr--multi-ai-advisor-mcp/badge.svg)](/listings/yuchenssr--multi-ai-advisor-mcp)

HTML

<a href="/listings/yuchenssr--multi-ai-advisor-mcp"><img src="/api/listings/yuchenssr--multi-ai-advisor-mcp/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

Installing via Smithery

To install multi-ai-advisor-mcp for Claude Desktop automatically via [Smithery](https://smithery.ai/server/@YuChenSSR/multi-ai-advisor-mcp):

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

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 193 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. # Multi-Model Advisor
  2. ## (锵锵四人行)
  3. [![smithery badge](https://smithery.ai/badge/@YuChenSSR/multi-ai-advisor-mcp)](https://smithery.ai/server/@YuChenSSR/multi-ai-advisor-mcp)
  4. 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.
  5. <a href="https://glama.ai/mcp/servers/@YuChenSSR/multi-ai-advisor-mcp">
  6. <img width="380" height="200" src="https://glama.ai/mcp/servers/@YuChenSSR/multi-ai-advisor-mcp/badge" alt="Multi-Model Advisor MCP server" />
  7. </a>
  8. ```mermaid
  9. graph TD
  10. A[Start] --> B[Worker Local AI 1 Opinion]
  11. A --> C[Worker Local AI 2 Opinion]
  12. A --> D[Worker Local AI 3 Opinion]
  13. B --> E[Manager AI]
  14. C --> E
  15. D --> E
  16. E --> F[Decision Made]
  17. ```
  18. ## Features
  19. - Query multiple Ollama models with a single question
  20. - Assign different roles/personas to each model
  21. - View all available Ollama models on your system
  22. - Customize system prompts for each model
  23. - Configure via environment variables
  24. - Integrate seamlessly with Claude for Desktop
  25. ## Prerequisites
  26. - Node.js 16.x or higher
  27. - Ollama installed and running (see [Ollama installation](https://github.com/ollama/ollama#installation))
  28. - Claude for Desktop (for the complete advisory experience)
  29. ## Installation
  30. ### Installing via Smithery
  31. To install multi-ai-advisor-mcp for Claude Desktop automatically via [Smithery](https://smithery.ai/server/@YuChenSSR/multi-ai-advisor-mcp):
  32. ```bash
  33. npx -y @smithery/cli install @YuChenSSR/multi-ai-advisor-mcp --client claude
  34. ```
  35. ### Manual Installation
  36. 1. Clone this repository:
  37. ```bash
  38. git clone https://github.com/YuChenSSR/multi-ai-advisor-mcp.git
  39. cd multi-ai-advisor-mcp
  40. ```
  41. 2. Install dependencies:
  42. ```bash
  43. npm install
  44. ```
  45. 3. Build the project:
  46. ```bash
  47. npm run build
  48. ```
  49. 4. Install required Ollama models:
  50. ```bash
  51. ollama pull gemma3:1b
  52. ollama pull llama3.2:1b
  53. ollama pull deepseek-r1:1.5b
  54. ```
  55. ## Configuration
  56. Create a `.env` file in the project root with your desired configuration:
  57. ```
  58. # Server configuration
  59. SERVER_NAME=multi-model-advisor
  60. SERVER_VERSION=1.0.0
  61. DEBUG=true
  62. # Ollama configuration
  63. OLLAMA_API_URL=http://localhost:11434
  64. DEFAULT_MODELS=gemma3:1b,llama3.2:1b,deepseek-r1:1.5b
  65. # System prompts for each model
  66. GEMMA_SYSTEM_PROMPT=You are a creative and innovative AI assistant. Think outside the box and offer novel perspectives.
  67. LLAMA_SYSTEM_PROMPT=You are a supportive and empathetic AI assistant focused on human well-being. Provide considerate and balanced advice.
  68. DEEPSEEK_SYSTEM_PROMPT=You are a logical and analytical AI assistant. Think step-by-step and explain your reasoning clearly.
  69. ```
  70. ## Connect to Claude for Desktop
  71. 1. Locate your Claude for Desktop configuration file:
  72. - MacOS: `~/Library/Application Support/Claude/claude_desktop_config.json`
  73. - Windows: `%APPDATA%\Claude\claude_desktop_config.json`
  74. 2. Edit the file to add the Multi-Model Advisor MCP server:
  75. ```json
  76. {
  77. "mcpServers": {
  78. "multi-model-advisor": {
  79. "command": "node",
  80. "args": ["/absolute/path/to/multi-ai-advisor-mcp/build/index.js"]
  81. }
  82. }
  83. }
  84. ```
  85. 3. Replace `/absolute/path/to/` with the actual path to your project directory
  86. 4. Restart Claude for Desktop
  87. ## Usage
  88. Once connected to Claude for Desktop, you can use the Multi-Model Advisor in several ways:
  89. ### List Available Models
  90. You can see all available models on your system:
  91. ```
  92. Show me which Ollama models are available on my system
  93. ```
  94. This will display all installed Ollama models and indicate which ones are configured as defaults.
  95. ### Basic Usage
  96. Simply ask Claude to use the multi-model advisor:
  97. ```
  98. what are the most important skills for success in today's job market,
  99. you can use gemma3:1b, llama3.2:1b, deepseek-r1:1.5b to help you
  100. ```
  101. Claude will query all default models and provide a synthesized response based on their different perspectives.
  102. ![example](https://raw.githubusercontent.com/YuChenSSR/pics/master/imgs/2025-03-24/Q53YEwdTaeTuL6a7.png)
  103. ## How It Works
  104. 1. The MCP server exposes two tools:
  105. - `list-available-models`: Shows all Ollama models on your system
  106. - `query-models`: Queries multiple models with a question
  107. 2. When you ask Claude a question referring to the multi-model advisor:
  108. - Claude decides to use the `query-models` tool
  109. - The server sends your question to multiple Ollama models
  110. - Each model responds with its perspective
  111. - Claude receives all responses and synthesizes a comprehensive answer
  112. 3. Each model can have a different "persona" or role assigned, encouraging diverse perspectives.
  113. ## Troubleshooting
  114. ### Ollama Connection Issues
  115. If the server can't connect to Ollama:
  116. - Ensure Ollama is running (`ollama serve`)
  117. - Check that the OLLAMA_API_URL is correct in your .env file
  118. - Try accessing http://localhost:11434 in your browser to verify Ollama is responding
  119. ### Model Not Found
  120. If a model is reported as unavailable:
  121. - Check that you've pulled the model using `ollama pull <model-name>`
  122. - Verify the exact model name using `ollama list`
  123. - Use the `list-available-models` tool to see all available models
  124. ### Claude Not Showing MCP Tools
  125. If the tools don't appear in Claude:
  126. - Ensure you've restarted Claude after updating the configuration
  127. - Check the absolute path in claude_desktop_config.json is correct
  128. - Look at Claude's logs for error messages
  129. ### RAM is not enough
  130. 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](#basic-usage)) or upgrading the memory.
  131. ## License
  132. MIT License
  133. For more details, please see the LICENSE file in [this project repository](https://github.com/YuChenSSR/multi-ai-advisor-mcp)
  134. ## Contributing
  135. Contributions are welcome! Please feel free to submit a Pull Request.

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.