Cognition Wheel

v1.0.0Coding Agentsstable

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.

cognition-wheelmcpai-integration
Share:
196
Stars
0
Downloads
0
Weekly
0/5

What is Cognition Wheel?

Cognition Wheel is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to 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....

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.

This server falls under the Coding Agents category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • A Model Context Protocol (MCP) server that implements a 'wis

Use Cases

Consult multiple state-of-the-art language models in parallel.
Synthesize diverse AI reasoning perspectives for better decisions.
Leverage wisdom-of-crowds approach to LLM outputs.
Hormold

Maintainer

LicenseMIT
Languagetypescript
Versionv1.0.0
UpdatedMay 13, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

Manual Installation

npx cognition-wheel

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use Cognition Wheel

Cognition Wheel is an MCP server that implements a 'wisdom of crowds' approach to AI reasoning by querying Claude (Opus), Gemini 2.5 Pro, and OpenAI O3 simultaneously and synthesizing their responses into a single high-quality answer. The server exposes a single `cognition_wheel` tool that sends your question to all three frontier models in parallel, uses anonymous code names (Alpha, Beta, Gamma) to reduce synthesis bias, and has one randomly-selected model produce the final synthesis. This multi-model consultation is ideal for complex decisions, code reviews, and research questions where a single model's blind spots could lead to suboptimal answers.

Prerequisites

  • Node.js 18 or higher
  • Anthropic API key (for Claude Opus access)
  • Google Generative AI API key (for Gemini 2.5 Pro access)
  • OpenAI API key (for O3 access)
  • An MCP-compatible client such as Claude Desktop, Cursor, or Claude Code
1

Obtain the three required API keys

Cognition Wheel queries Claude Opus, Gemini 2.5 Pro, and OpenAI O3 in parallel. You need valid API keys for all three providers before the server will function. Get them from console.anthropic.com, aistudio.google.com, and platform.openai.com respectively.

2

Add to your MCP client configuration

The easiest installation method is npx — no global install required. Add the server to your MCP client config with all three API keys as environment variables.

{
  "mcpServers": {
    "cognition-wheel": {
      "command": "npx",
      "args": ["-y", "mcp-cognition-wheel"],
      "env": {
        "ANTHROPIC_API_KEY": "your_anthropic_key",
        "GOOGLE_GENERATIVE_AI_API_KEY": "your_google_key",
        "OPENAI_API_KEY": "your_openai_key"
      }
    }
  }
}
3

Alternatively, install globally

For frequent use, install the package globally so it starts faster without npx resolution delay.

npm install -g mcp-cognition-wheel
mcp-cognition-wheel
4

Build from source (optional)

To modify the server or run the latest unreleased version, clone the repository and build it manually.

git clone https://github.com/Hormold/cognition-wheel
cd cognition-wheel
pnpm install
cp .env.example .env
# Edit .env with your API keys
pnpm run build
5

Use the cognition_wheel tool in your AI client

Once connected, invoke the cognition_wheel tool with a context and question. The tool will consult all three frontier models and return a synthesized answer. Optionally enable internet search for current information.

Cognition Wheel Examples

Client configuration (Cursor)

Add Cognition Wheel to Cursor's MCP configuration file at .cursor/mcp.json with all required API keys.

{
  "mcpServers": {
    "cognition-wheel": {
      "command": "npx",
      "args": ["-y", "mcp-cognition-wheel"],
      "env": {
        "ANTHROPIC_API_KEY": "your_anthropic_key",
        "GOOGLE_GENERATIVE_AI_API_KEY": "your_google_key",
        "OPENAI_API_KEY": "your_openai_key"
      }
    }
  }
}

Prompts to try

Use Cognition Wheel when you want consensus from multiple frontier AI models rather than a single perspective.

- "Use cognition_wheel to review this architectural decision: should we use microservices or a monolith for a team of 5?"
- "Ask all three models whether this SQL query has any performance issues: SELECT * FROM orders JOIN customers..."
- "Get a multi-model consensus on the best approach to implement rate limiting in a Node.js API"
- "Use wisdom-of-crowds reasoning to evaluate the pros and cons of switching from REST to GraphQL"
- "Have multiple models review this code for security vulnerabilities"

Troubleshooting Cognition Wheel

cognition_wheel tool fails with authentication error for one provider

Each API key is checked independently. Verify all three keys are valid: ANTHROPIC_API_KEY (starts with sk-ant-), GOOGLE_GENERATIVE_AI_API_KEY (starts with AIza...), and OPENAI_API_KEY (starts with sk-). Ensure none have expired or exceeded quotas.

Responses are slow or time out

The tool queries O3, Claude Opus, and Gemini 2.5 Pro in parallel — these are large models with higher latency. Complex questions can take 30-60 seconds. Ensure your MCP client has a sufficiently long tool timeout (at least 120 seconds). If one provider is down, the tool may fail entirely.

npx command fails to find mcp-cognition-wheel package

Ensure you have Node.js 18+ and a working internet connection. Try `npm install -g mcp-cognition-wheel` for a one-time global install, then use `mcp-cognition-wheel` as the command in your config instead of npx.

Frequently Asked Questions about Cognition Wheel

What is Cognition Wheel?

Cognition Wheel is a Model Context Protocol (MCP) server that 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. It connects AI assistants to external tools and data sources through a standardized interface.

How do I install Cognition Wheel?

Follow the installation instructions on the Cognition Wheel GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with Cognition Wheel?

Cognition Wheel works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is Cognition Wheel free to use?

Yes, Cognition Wheel is open source and available under the MIT license. You can use it freely in both personal and commercial projects.

Browse More Coding Agents MCP Servers

Explore all coding agents servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Quick Config Preview

{ "mcpServers": { "cognition-wheel": { "command": "npx", "args": ["-y", "cognition-wheel"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use Cognition Wheel?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides