{"id":26937358,"url":"https://github.com/YuChenSSR/multi-ai-advisor-mcp","last_synced_at":"2025-04-02T13:15:13.239Z","repository":{"id":284186057,"uuid":"954021177","full_name":"YuChenSSR/multi-ai-advisor-mcp","owner":"YuChenSSR","description":"council of models for decision","archived":false,"fork":false,"pushed_at":"2025-03-24T15:44:17.000Z","size":6510,"stargazers_count":1,"open_issues_count":1,"forks_count":1,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-03-24T16:33:18.636Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"","language":"TypeScript","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/YuChenSSR.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2025-03-24T12:52:06.000Z","updated_at":"2025-03-24T15:48:45.000Z","dependencies_parsed_at":"2025-03-24T16:44:23.698Z","dependency_job_id":null,"html_url":"https://github.com/YuChenSSR/multi-ai-advisor-mcp","commit_stats":null,"previous_names":["yuchenssr/multi-ai-advisor-mcp"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/YuChenSSR%2Fmulti-ai-advisor-mcp","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/YuChenSSR%2Fmulti-ai-advisor-mcp/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/YuChenSSR%2Fmulti-ai-advisor-mcp/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/YuChenSSR%2Fmulti-ai-advisor-mcp/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/YuChenSSR","download_url":"https://codeload.github.com/YuChenSSR/multi-ai-advisor-mcp/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":246819773,"owners_count":20839095,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2025-04-02T13:15:09.991Z","updated_at":"2025-04-02T13:15:13.186Z","avatar_url":"https://github.com/YuChenSSR.png","language":"TypeScript","funding_links":[],"categories":["AI Agents","Ai Integration Mcp Servers","Community Servers","پیاده‌سازی‌های سرور","Content Creation","Developer Tools","🌐 Web Development","Table of Contents"],"sub_categories":["Reasoning \u0026 Prompts","💻 \u003ca name=\"developer-tools\"\u003e\u003c/a\u003eابزارهای توسعه‌دهنده","AI Services"],"readme":"# Multi-Model Advisor\n## (锵锵四人行)\n\n[![smithery badge](https://smithery.ai/badge/@YuChenSSR/multi-ai-advisor-mcp)](https://smithery.ai/server/@YuChenSSR/multi-ai-advisor-mcp)\n\nA 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.\n\n\u003ca href=\"https://glama.ai/mcp/servers/@YuChenSSR/multi-ai-advisor-mcp\"\u003e\n  \u003cimg width=\"380\" height=\"200\" src=\"https://glama.ai/mcp/servers/@YuChenSSR/multi-ai-advisor-mcp/badge\" alt=\"Multi-Model Advisor MCP server\" /\u003e\n\u003c/a\u003e\n\n```mermaid\ngraph TD\n    A[Start] --\u003e B[Worker Local AI 1 Opinion]\n    A --\u003e C[Worker Local AI 2 Opinion]\n    A --\u003e D[Worker Local AI 3 Opinion]\n    B --\u003e E[Manager AI]\n    C --\u003e E\n    D --\u003e E\n    E --\u003e F[Decision Made]\n```\n\n## Features\n\n- Query multiple Ollama models with a single question\n- Assign different roles/personas to each model\n- View all available Ollama models on your system\n- Customize system prompts for each model\n- Configure via environment variables\n- Integrate seamlessly with Claude for Desktop\n\n## Prerequisites\n\n- Node.js 16.x or higher\n- Ollama installed and running (see [Ollama installation](https://github.com/ollama/ollama#installation))\n- Claude for Desktop (for the complete advisory experience)\n\n## Installation\n\n### Installing via Smithery\n\nTo install multi-ai-advisor-mcp for Claude Desktop automatically via [Smithery](https://smithery.ai/server/@YuChenSSR/multi-ai-advisor-mcp):\n\n```bash\nnpx -y @smithery/cli install @YuChenSSR/multi-ai-advisor-mcp --client claude\n```\n\n### Manual Installation\n1. Clone this repository:\n   ```bash\n   git clone https://github.com/yourusername/multi-model-advisor.git\n   cd multi-model-advisor\n   ```\n\n2. Install dependencies:\n   ```bash\n   npm install\n   ```\n\n3. Build the project:\n   ```bash\n   npm run build\n   ```\n\n4. Install required Ollama models:\n   ```bash\n   ollama pull gemma3:1b\n   ollama pull llama3.2:1b\n   ollama pull deepseek-r1:1.5b\n   ```\n\n## Configuration\n\nCreate a `.env` file in the project root with your desired configuration:\n\n```\n# Server configuration\nSERVER_NAME=multi-model-advisor\nSERVER_VERSION=1.0.0\nDEBUG=true\n\n# Ollama configuration\nOLLAMA_API_URL=http://localhost:11434\nDEFAULT_MODELS=gemma3:1b,llama3.2:1b,deepseek-r1:1.5b\n\n# System prompts for each model\nGEMMA_SYSTEM_PROMPT=You are a creative and innovative AI assistant. Think outside the box and offer novel perspectives.\nLLAMA_SYSTEM_PROMPT=You are a supportive and empathetic AI assistant focused on human well-being. Provide considerate and balanced advice.\nDEEPSEEK_SYSTEM_PROMPT=You are a logical and analytical AI assistant. Think step-by-step and explain your reasoning clearly.\n```\n\n## Connect to Claude for Desktop\n\n1. Locate your Claude for Desktop configuration file:\n   - MacOS: `~/Library/Application Support/Claude/claude_desktop_config.json`\n   - Windows: `%APPDATA%\\Claude\\claude_desktop_config.json`\n\n2. Edit the file to add the Multi-Model Advisor MCP server:\n\n```json\n{\n  \"mcpServers\": {\n    \"multi-model-advisor\": {\n      \"command\": \"node\",\n      \"args\": [\"/absolute/path/to/multi-model-advisor/build/index.js\"]\n    }\n  }\n}\n```\n\n3. Replace `/absolute/path/to/` with the actual path to your project directory\n\n4. Restart Claude for Desktop\n\n## Usage\n\nOnce connected to Claude for Desktop, you can use the Multi-Model Advisor in several ways:\n\n### List Available Models\n\nYou can see all available models on your system:\n\n```\nShow me which Ollama models are available on my system\n```\n\nThis will display all installed Ollama models and indicate which ones are configured as defaults.\n\n### Basic Usage\n\nSimply ask Claude to use the multi-model advisor:\n\n```\nwhat are the most important skills for success in today's job market, \nyou can use gemma3:1b, llama3.2:1b, deepseek-r1:1.5b to help you \n```\n\nClaude will query all default models and provide a synthesized response based on their different perspectives.\n\n![example](https://raw.githubusercontent.com/YuChenSSR/pics/master/imgs/2025-03-24/Q53YEwdTaeTuL6a7.png)\n\n\n\n## How It Works\n\n1. The MCP server exposes two tools:\n   - `list-available-models`: Shows all Ollama models on your system\n   - `query-models`: Queries multiple models with a question\n\n2. When you ask Claude a question referring to the multi-model advisor:\n   - Claude decides to use the `query-models` tool\n   - The server sends your question to multiple Ollama models\n   - Each model responds with its perspective\n   - Claude receives all responses and synthesizes a comprehensive answer\n\n3. Each model can have a different \"persona\" or role assigned, encouraging diverse perspectives.\n\n## Troubleshooting\n\n### Ollama Connection Issues\n\nIf the server can't connect to Ollama:\n- Ensure Ollama is running (`ollama serve`)\n- Check that the OLLAMA_API_URL is correct in your .env file\n- Try accessing http://localhost:11434 in your browser to verify Ollama is responding\n\n### Model Not Found\n\nIf a model is reported as unavailable:\n- Check that you've pulled the model using `ollama pull \u003cmodel-name\u003e`\n- Verify the exact model name using `ollama list`\n- Use the `list-available-models` tool to see all available models\n\n### Claude Not Showing MCP Tools\n\nIf the tools don't appear in Claude:\n- Ensure you've restarted Claude after updating the configuration\n- Check the absolute path in claude_desktop_config.json is correct\n- Look at Claude's logs for error messages\n\n### RAM is not enough\n\nSome 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.\n\n## License\n\nMIT License\n\nFor more details, please see the LICENSE file in [this project repository](https://github.com/YuChenSSR/multi-ai-advisor-mcp)\n\n## Contributing\n\nContributions are welcome! Please feel free to submit a Pull Request.","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FYuChenSSR%2Fmulti-ai-advisor-mcp","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FYuChenSSR%2Fmulti-ai-advisor-mcp","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FYuChenSSR%2Fmulti-ai-advisor-mcp/lists"}