Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| GEMINI_API_KEY | Yes | Your Google Gemini API key |
Schema
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| escalate_analysis | Hand off complex analysis to Gemini when Claude Code hits reasoning limits. Gemini will perform deep semantic analysis beyond syntactic patterns. |
| trace_execution_path | Use Gemini to perform deep execution analysis with semantic understanding |
| hypothesis_test | Use Gemini to test specific theories about code behavior |
| cross_system_impact | Use Gemini to analyze changes across service boundaries |
| performance_bottleneck | Use Gemini for deep performance analysis with execution modeling |
| start_conversation | Start a conversational analysis session between Claude and Gemini |
| continue_conversation | Continue an ongoing analysis conversation |
| finalize_conversation | Complete the conversation and get final analysis results |
| get_conversation_status | Check the status and progress of an ongoing conversation |
| run_hypothesis_tournament | Run a competitive hypothesis tournament to find root causes. Multiple AI conversations test different theories in parallel, with evidence-based scoring and elimination rounds. |