Deep Code Reasoning MCP Server

Deep Code Reasoning MCP Server - Specialized analysis tool for complex codebases

Local serverstdioTypeScript

What is the Deep Code Reasoning MCP MCP server?

Deep Code Reasoning MCP becomes available to MCP clients through the deep code reasoning mcp mcp server. Deep Code Reasoning MCP Server - Specialized analysis tool for complex codebases.

What Deep Code Reasoning MCP does

An MCP server that pairs Claude Code with Google's Gemini AI for complementary code analysis. This server enables a multi-model workflow where Claude Code handles tight 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.

Key capabilities

  • Gemini 2.5 Pro Preview — Uses Google's latest Gemini 2.5 Pro Preview (05-06) model with 1M token context window
  • Conversational Analysis — NEW! AI-to-AI dialogues between Claude and Gemini for iterative problem-solving
  • Execution Flow Tracing — Understands data flow and state transformations, not just function calls
  • Cross-System Impact Analysis — Models how changes propagate across service boundaries
  • Performance Modeling — Identifies N+1 patterns, memory leaks, and algorithmic bottlenecks
  • Hypothesis Testing — Tests theories about code behavior with evidence-based validation
  • Long Context Support — Leverages Gemini 2.5 Pro Preview's 1M token context for analyzing large codebases

Tools it exposes

Once connected, the assistant can call these 9 tools directly:

  • start_conversation — Initiates a conversational analysis session between Claude and Gemini
  • continue_conversation — Continues an active conversation with Claude's response or follow-up question
  • finalize_conversation — Completes the conversation and generates structured analysis results
  • get_conversation_status — The get_conversation_status tool exposed by this server
  • escalate_analysis — Main tool for handing off complex analysis from Claude Code to Gemini
  • trace_execution_path — Deep execution analysis with Gemini's semantic understanding
  • cross_system_impact — The cross_system_impact tool exposed by this server
  • performance_bottleneck — The performance_bottleneck tool exposed by this server
  • hypothesis_test — The hypothesis_test tool exposed by this server

Installing the deep code reasoning mcp mcp server

Setup follows the standard MCP pattern: clone or install the server, then register it in your client's configuration file and restart the client. The configuration snippets on this page cover Claude Desktop, Claude Code and Cursor.

Configuration

Before the server will start you need to supply one environment variable: GEMINI_API_KEY. Keep credentials in your client's env block or a secrets manager rather than committing them.

Requirements

  • Node.js 18 or later - A Google Cloud account with Gemini API access - Gemini API key from Google AI Studio

Where it fits

Developer-tool servers are usually the first ones people connect, because they turn "help me with this code" into an assistant that can actually read the repo and act on it. Deep Code Reasoning MCP sits in that group, and the shape of its toolset — start_conversation, continue_conversation, finalize_conversation among others — tells you what it is really for. Worth comparing against the other developer tools servers in this directory before you commit to one, since several overlap in scope but differ sharply in setup cost and permissions.

Practical notes

  • This server runs locally, so it operates with whatever access your machine and its credentials already have. Scope that deliberately rather than by default.
  • It will not start until its required credentials are present, so set those before wondering why the tools never appear.
  • With 9 tools exposed, expect a noticeable bump in prompt size — disable it in projects that never use Deep Code Reasoning MCP.
  • Maintained by haasonsaas, written in TypeScript.
  • MCP clients ask for confirmation before each tool call by default. Keep that on while you learn what the deep code reasoning mcp mcp server actually does with your data.
  • Every entry in this directory is reviewed by hand before it goes live, and details are checked against the project's own documentation.

Available tools

ToolWhat it does
start_conversationInitiates a conversational analysis session between Claude and Gemini.
continue_conversationContinues an active conversation with Claude's response or follow-up question.
finalize_conversationCompletes the conversation and generates structured analysis results.
get_conversation_statusThe get_conversation_status tool exposed by this server.
escalate_analysisMain tool for handing off complex analysis from Claude Code to Gemini.
trace_execution_pathDeep execution analysis with Gemini's semantic understanding.
cross_system_impactThe cross_system_impact tool exposed by this server.
performance_bottleneckThe performance_bottleneck tool exposed by this server.
hypothesis_testThe hypothesis_test tool exposed by this server.

How to install the Deep Code Reasoning MCP MCP server

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

Configuration as documented by the project. Restart the client after saving.

Configuration

  • Node.js 18 or later - A Google Cloud account with Gemini API access - Gemini API key from Google AI Studio
VariableDescriptionRequired
GEMINI_API_KEYCredential the server authenticates with.Yes

Example prompts to try

  • Use Deep Code Reasoning MCP to start conversation.
  • Use Deep Code Reasoning MCP to continue conversation.
  • Use Deep Code Reasoning MCP to finalize conversation.

Frequently asked questions

It connects Deep Code Reasoning MCP to MCP-compatible AI assistants such as Claude and Cursor, exposing 9 tools (start_conversation, continue_conversation, finalize_conversation, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Deep Code Reasoning MCP directly.