{"id":29104418,"url":"https://github.com/hormold/cognition-wheel","last_synced_at":"2026-01-21T13:25:20.613Z","repository":{"id":299163467,"uuid":"1002250785","full_name":"Hormold/cognition-wheel","owner":"Hormold","description":"A Model Context Protocol (MCP) server that implements a \"wisdom of crowds\" approach to AI reasoning by consulting multiple state-of-the-art language models in parallel and synthesizing their responses.","archived":false,"fork":false,"pushed_at":"2025-06-15T03:55:19.000Z","size":11,"stargazers_count":196,"open_issues_count":3,"forks_count":11,"subscribers_count":1,"default_branch":"main","last_synced_at":"2026-01-19T22:49:12.222Z","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":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/Hormold.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"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,"zenodo":null}},"created_at":"2025-06-15T03:45:12.000Z","updated_at":"2026-01-09T23:58:54.000Z","dependencies_parsed_at":null,"dependency_job_id":"766a8dab-fdca-4802-9578-6987d1cfbaa6","html_url":"https://github.com/Hormold/cognition-wheel","commit_stats":null,"previous_names":["hormold/cognition-wheel"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/Hormold/cognition-wheel","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Hormold%2Fcognition-wheel","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Hormold%2Fcognition-wheel/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Hormold%2Fcognition-wheel/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Hormold%2Fcognition-wheel/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Hormold","download_url":"https://codeload.github.com/Hormold/cognition-wheel/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Hormold%2Fcognition-wheel/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":28633757,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-01-21T04:47:28.174Z","status":"ssl_error","status_checked_at":"2026-01-21T04:47:22.943Z","response_time":86,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.5:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"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":"2025-06-29T00:04:53.655Z","updated_at":"2026-01-21T13:25:20.601Z","avatar_url":"https://github.com/Hormold.png","language":"TypeScript","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Cognition Wheel MCP Server\n\nA Model Context Protocol (MCP) server that implements a \"wisdom of crowds\" approach to AI reasoning by consulting multiple state-of-the-art language models in parallel and synthesizing their responses.\n\n## Quick Start\n\n### Option 1: Use with npx (Recommended)\n\n```bash\n# Run directly with npx (no installation needed)\nnpx mcp-cognition-wheel\n\n# Or install globally\nnpm install -g mcp-cognition-wheel\nmcp-cognition-wheel\n```\n\n### Option 2: Build from source\n\n1. Clone the repository\n2. Install dependencies: `pnpm install`\n3. Copy `.env.example` to `.env` and add your API keys\n4. Build the project: `pnpm run build`\n\n## How It Works\n\nThe Cognition Wheel follows a three-phase process:\n\n1. **Parallel Consultation**: Simultaneously queries three different AI models:\n   - Claude-4-Opus (Anthropic)\n   - Gemini-2.5-Pro (Google)\n   - O3 (OpenAI)\n\n2. **Anonymous Analysis**: Uses code names (Alpha, Beta, Gamma) to eliminate bias during the synthesis phase\n\n3. **Smart Synthesis**: Randomly selects one of the models to act as a synthesizer, which analyzes all responses and produces a final, comprehensive answer\n\n## Features\n\n- **Parallel Processing**: All models are queried simultaneously for faster results\n- **Bias Reduction**: Anonymous code names prevent synthesizer bias toward specific models\n- **Internet Search**: Optional web search capabilities for all models\n- **Detailed Logging**: Comprehensive debug logs for transparency and troubleshooting\n- **Robust Error Handling**: Graceful degradation when individual models fail\n\n## Installation\n\n### Option 1: Use with npx (Recommended)\n\n```bash\n# Run directly with npx (no installation needed)\nnpx mcp-cognition-wheel\n\n# Or install globally\nnpm install -g mcp-cognition-wheel\nmcp-cognition-wheel\n```\n\n### Option 2: Build from source\n\n1. Clone the repository\n2. Install dependencies: `pnpm install`\n3. Copy `.env.example` to `.env` and add your API keys\n4. Build the project: `pnpm run build`\n\n## Usage\n\nThis is an MCP server designed to be used with MCP-compatible clients like Claude Desktop or other MCP tools.\n\n### Required Environment Variables\n\n- `ANTHROPIC_API_KEY`: Your Anthropic API key\n- `GOOGLE_GENERATIVE_AI_API_KEY`: Your Google AI API key  \n- `OPENAI_API_KEY`: Your OpenAI API key\n\n### Using with Cursor\n\nBased on the guide from [this dev.to article](https://dev.to/andyrewlee/use-your-own-mcp-on-cursor-in-5-minutes-1ag4), here's how to integrate with Cursor:\n\n#### Option 1: Using npx (Recommended)\n\n1. **Open Cursor Settings**:\n   - Go to Settings → MCP\n   - Click \"Add new MCP server\"\n\n2. **Configure the server**:\n   - **Name**: `cognition-wheel`\n   - **Command**: `npx`\n   - **Args**: `[\"-y\", \"mcp-cognition-wheel\"]`\n   \n   Example configuration:\n   ```json\n   {\n     \"cognition-wheel\": {\n       \"command\": \"npx\",\n       \"args\": [\"-y\", \"mcp-cognition-wheel\"],\n       \"env\": {\n         \"ANTHROPIC_API_KEY\": \"your_anthropic_key\",\n         \"GOOGLE_GENERATIVE_AI_API_KEY\": \"your_google_key\", \n         \"OPENAI_API_KEY\": \"your_openai_key\"\n       }\n     }\n   }\n   ```\n\n#### Option 2: Using local build\n\n1. **Build the project** (if not already done):\n   ```bash\n   pnpm run build\n   ```\n\n2. **Configure the server**:\n   - **Name**: `cognition-wheel`\n   - **Command**: `node`\n   - **Args**: `[\"/absolute/path/to/your/cognition-wheel/dist/app.js\"]`\n   \n   Example configuration:\n   ```json\n   {\n     \"cognition-wheel\": {\n       \"command\": \"node\",\n       \"args\": [\n         \"/Users/yourname/path/to/cognition-wheel/dist/app.js\"\n       ],\n       \"env\": {\n         \"ANTHROPIC_API_KEY\": \"your_anthropic_key\",\n         \"GOOGLE_GENERATIVE_AI_API_KEY\": \"your_google_key\", \n         \"OPENAI_API_KEY\": \"your_openai_key\"\n       }\n     }\n   }\n   ```\n\n3. **Test the integration**:\n   - Enter Agent mode in Cursor\n   - Ask a complex question that would benefit from multiple AI perspectives\n   - The `cognition_wheel` tool should be automatically triggered\n\n### Tool Usage\n\nThe server provides a single tool called `cognition_wheel` with the following parameters:\n\n- `context`: Background information and context for the problem\n- `question`: The specific question you want answered\n- `enable_internet_search`: Boolean flag to enable web search capabilities\n\n## Development\n\n- `pnpm run dev`: Watch mode for development\n- `pnpm run build`: Build the TypeScript code\n- `pnpm run start`: Run the server directly with tsx\n\n## Docker\n\nBuild and run with Docker:\n\n```bash\n# Build the image\ndocker build -t cognition-wheel .\n\n# Run with environment variables\ndocker run --rm \\\n  -e ANTHROPIC_API_KEY=your_key \\\n  -e GOOGLE_GENERATIVE_AI_API_KEY=your_key \\\n  -e OPENAI_API_KEY=your_key \\\n  cognition-wheel\n```\n\n## License\n\nMIT ","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhormold%2Fcognition-wheel","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fhormold%2Fcognition-wheel","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhormold%2Fcognition-wheel/lists"}