deep-code-reasoning-mcp

Overview

This MCP server creates a multi-model workflow where Claude Code handles terminal integration and multi-file refactoring, while Gemini leverages its massive context window (1M tokens) and code execution capabilities for distributed system debugging and long-trace analysis. It provides intelligent routing between the two models based on specific strengths of each AI system.

Try asking AI

After installing, here are 5 things you can ask your AI assistant:

• start_conversation{claude_context: {attempted_approaches: string[], partial_findings: any[], stuck_description: string, code_scope: {files: string[], entry_points?: CodeLocation[], service_names?: string[]}}, analysis_type: 'execution_trace' | 'cross_system'

  Initiates a conversational analysis session between Claude and Gemini.

  Try:Start a conversation to analyze performance issues in the UserServiceTry:Begin a cross-system impact analysis of these code changes
• continue_conversation{session_id: string, message: string, include_code_snippets?: boolean}

  Continues an active conversation with Claude's response or follow-up question.

  Try:Continue the conversation with a question about query optimizationTry:Follow up with a request for more context about the race condition
• finalize_conversation{session_id: string, summary_format: 'detailed' | 'concise' | 'actionable'}

  Completes the conversation and generates structured analysis results.

  Try:Finalize the conversation and provide actionable recommendationsTry:Complete the analysis with a detailed summary of findings
• get_conversation_status{session_id: string}

  Checks the status and progress of an ongoing conversation.

  Try:What's the status of our conversation session?Try:Check if the analysis is complete
• escalate_analysis{claude_context: {attempted_approaches: string[], partial_findings: any[], stuck_description: string, code_scope: {files: string[], entry_points?: CodeLocation[], service_names?: string[]}}, analysis_type: 'execution_trace' | 'cross_system'

  Main tool for handing off complex analysis from Claude Code to Gemini.

  Try:Escalate this distributed system analysis to GeminiTry:Hand off the performance regression investigation
• trace_execution_path{entry_point: {file: string, line: number, function_name?: string}, max_depth?: number, include_data_flow?: boolean}

  Deep execution analysis with Gemini's semantic understanding.

  Try:Trace the execution path of this functionTry:Analyze the data flow starting from this line of code
• cross_system_impact{change_scope: {files: string[], service_names?: string[]}, impact_types?: ('breaking' | 'performance' | 'behavioral')[]}

  Analyze impacts across service boundaries.

  Try:What's the cross-system impact of changing this API?Try:Analyze how these changes might affect other services
• performance_bottleneck{code_path: {entry_point: {file: string, line: number, function_name?: string}, suspected_issues?: string[]}, profile_depth?: 1-5}

  Deep performance analysis beyond simple profiling.

  Try:Identify performance bottlenecks in this functionTry:Analyze the slow database queries in the user service
• hypothesis_test{hypothesis: string, code_scope: {files: string[], entry_points?: CodeLocation[]}, test_approach: string}

  Test specific theories about code behavior.

  Try:Test the hypothesis that the memory leak is caused by this functionTry:Validate the theory that race conditions occur under high load

Comparable tools

Installation

git clone https://github.com/Haasonsaas/deep-code-reasoning-mcp.git
cd deep-code-reasoning-mcp

npm install

cp .env.example .env
# Edit .env and add your GEMINI_API_KEY

npm run build

{
  "mcpServers": {
    "deep-code-reasoning": {
      "command": "node",
      "args": ["/path/to/deep-code-reasoning-mcp/dist/index.js"],
      "env": {
        "GEMINI_API_KEY": "your-gemini-api-key"
      }
    }
  }
}

FAQ

What makes this server different from other AI code analysis tools?

It combines the strengths of two AI models - Claude Code for local-context operations and CLI-native workflows, and Gemini with its 1M token context for large-scale codebase analysis and distributed system debugging.

What are the prerequisites to use this MCP server?

You need Node.js 18 or later, a Google Cloud account with Gemini API access, and a Gemini API key from Google AI Studio.

Compare deep-code-reasoning-mcp with