🧠 MCP Code Assistant
@kiranimmadi2
MCP-Based AI Code Analysis Tool: Enables LLM agents to interact with, analyze, and debug codebases via structured MCP tool calls — scanning project structure, extracting code elements, and detecting Python anti-patterns.
Overview
What is 🧠 MCP Code Assistant?
🧠 MCP Code Assistant is an AI‑powered developer tool built on the Model Context Protocol (MCP). It enables LLM agents to scan, analyze, and debug codebases through structured MCP tool calls, exposing project structure, code elements (classes, functions, imports), and Python anti‑pattern detection – without requiring manual context injection.
How to use 🧠 MCP Code Assistant?
Clone the repository and run python mcp.py /path/to/your/project with command‑line options such as --scan, --structure, --analyze <file>, --search <regex>, or --bugs. It can also be imported as a Python library (from mcp import MCP) to produce structured outputs for LLM consumption.
Key features of 🧠 MCP Code Assistant
- Scans entire project structure and identifies all code files
- Extracts classes, functions, imports, and global variables from Python files
- Searches codebase for patterns using regular expressions
- Detects common Python bugs and anti‑patterns
- Updates file content programmatically
- Works with pure Python standard library – no external dependencies
Use cases of 🧠 MCP Code Assistant
- AI agents navigate and understand an unfamiliar codebase autonomously
- Automated code review: detect bugs and anti‑patterns across Python files
- LLM‑powered refactoring: analyze and modify code via structured tool calls
- Continuous project mapping: generate up‑to‑date structure and element overviews
FAQ from 🧠 MCP Code Assistant
What are the system requirements?
Python 3.6 or higher; no external libraries are needed – only the Python standard library is used.
How do I install it?
Clone the repository from GitHub (git clone https://github.com/kiranimmadi2/MCP-Server.git) and change into the MCP-Server directory.
Can 🧠 MCP Code Assistant analyze non‑Python files?
Currently, analysis (extracting classes, functions, imports, and bug detection) is focused on Python files. Support for JavaScript and TypeScript is listed on the roadmap.
Is it a full MCP server now?
The current version exposes functionality via CLI and as a Python library. The roadmap includes implementing full MCP server mode with JSON‑RPC tool registration and LLM agent integration examples.
What license is used?
The project is released under the MIT License.
