cognition-wheel
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| OPENAI_API_KEY | Yes | Your OpenAI API key | |
| ANTHROPIC_API_KEY | Yes | Your Anthropic API key | |
| GOOGLE_GENERATIVE_AI_API_KEY | Yes | Your Google AI API key |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| cognition_wheelA | A tool that consults three AI models (Claude Opus, Gemini 2.0, GPT-4) in parallel, then uses one of them to synthesize the results into a single, high-quality answer. Use this for complex questions requiring deep analysis and verification. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 1 tool
Only one tool exists, leaving no room for ambiguity or confusion between tools.
With a single tool, the naming is trivially consistent using snake_case.
A single tool for this specialized purpose is acceptable but minimal; the server could benefit from additional tools for subtasks like model selection or intermediate result access.
The one tool covers the entire synthesis workflow, but there are obvious gaps, such as lack of configuration options, error handling per model, or ability to query models individually.