Code Expert System MCP Server

Simulate code reviews from expert personas using AI and a knowledge graph.

Local serverstdioPython★ 3

What is the Code Expert System MCP Server?

Simulate code reviews from expert personas using AI and a knowledge graph.

What the server does

A Python-based code review system using the Model Context Protocol (MCP). It provides code review capabilities through simulated expert personas like Martin Fowler and Robert C. Martin (Uncle Bob).

  • Code review based on Martin Fowler's refactoring principles
  • Code review based on Robert C. Martin's Clean Code principles
  • Knowledge graph storage of code, reviews, and relationships
  • Integration with Ollama for AI-powered reviews
  • Server-side Event (SSE) support for web integration

More MCP options

Compare MCP servers by category, or browse hosted MCP servers if you prefer an endpoint over a local process.

Maintainer setup documentation.

Recorded tools

Check the linked publisher documentation and your connected client's tool list. Names and availability can vary with the server version and account permissions.

ToolWhat it does
ask_martinAsk Martin Fowler to review code and suggest refactorings
ask_bobAsk Robert C. Martin (Uncle Bob) to review code based on Clean Code principles
read_graphRead the entire knowledge graph
search_nodesSearch for nodes in the knowledge graph
open_nodesOpen specific nodes by their names

Configuration

VariableDescriptionRequired
KNOWLEDGE_GRAPH_PATHFilesystem location the server is allowed to use.Optional
OLLAMA_HOSTEndpoint or connection string the server talks to.Optional

Example prompts to try

  • “Use Code Expert System to ask martin.”
  • “Use Code Expert System to ask bob.”
  • “Use Code Expert System to read graph.”

Frequently asked questions

It leverages AI models through Ollama to analyze your code against expert principles (e.g., Fowler's refactoring, Uncle Bob's Clean Code). The results are stored in a knowledge graph for future reference and analysis.