🧠 MCP Code Assistant

by kiranimmadi2

1 stars

277 downloads

Not rated

GitHub

Developer Tools

About

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.

Details

Author: kiranimmadi2
GitHub stars: 1
Downloads: 277
Categories: Developer Tools

- 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

Setting up with Highlight

This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:

Download and install Highlight from highlightai.com/download
Navigate to the plugins tab and select "Add Custom Plugin"
Configure the plugin with the settings below

Plugin Name 🧠 MCP Code Assistant

Command (node, npx, python, etc.)

Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
Enable "Start Automatically" if you want the plugin to start when Highlight launches

Setting up with Cursor

Open Cursor's settings
Navigate to the MCP section
Click "Add new Global MCP server"
Copy and paste the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "\ud83e\udde0 mcp code assistant": {
            "mcp-server-kiranimmadi2": {
                "command": "python",
                "args": [
                    "mcp.py",
                    "/path/to/your/project",
                    "[options]"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "\ud83e\udde0 mcp code assistant": {
            "mcp-server-kiranimmadi2": {
                "command": "python",
                "args": [
                    "mcp.py",
                    "/path/to/your/project",
                    "[options]"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "\ud83e\udde0 mcp code assistant": {
            "mcp-server-kiranimmadi2": {
                "command": "python",
                "args": [
                    "mcp.py",
                    "/path/to/your/project",
                    "[options]"
                ]
            }
        }
    }
}

Setting up with Claude Desktop

Open Claude Desktop's settings
Go to the Integrations tab
Click "Add MCP Server"
Use the configuration below based on your operating system

Note: Make sure Claude Desktop is running before attempting to connect.

JSON

{
    "mcpServers": {
        "\ud83e\udde0 mcp code assistant": {
            "mcp-server-kiranimmadi2": {
                "command": "python",
                "args": [
                    "mcp.py",
                    "/path/to/your/project",
                    "[options]"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "\ud83e\udde0 mcp code assistant": {
            "mcp-server-kiranimmadi2": {
                "command": "python",
                "args": [
                    "mcp.py",
                    "/path/to/your/project",
                    "[options]"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "\ud83e\udde0 mcp code assistant": {
            "mcp-server-kiranimmadi2": {
                "command": "python",
                "args": [
                    "mcp.py",
                    "/path/to/your/project",
                    "[options]"
                ]
            }
        }
    }
}

Setting up with Windsurf

Open Windsurf's preferences
Go to the Integrations section
Click "Add MCP Integration"
Use the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "\ud83e\udde0 mcp code assistant": {
            "mcp-server-kiranimmadi2": {
                "command": "python",
                "args": [
                    "mcp.py",
                    "/path/to/your/project",
                    "[options]"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "\ud83e\udde0 mcp code assistant": {
            "mcp-server-kiranimmadi2": {
                "command": "python",
                "args": [
                    "mcp.py",
                    "/path/to/your/project",
                    "[options]"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "\ud83e\udde0 mcp code assistant": {
            "mcp-server-kiranimmadi2": {
                "command": "python",
                "args": [
                    "mcp.py",
                    "/path/to/your/project",
                    "[options]"
                ]
            }
        }
    }
}

Setting up with Cline

Open Cline's settings
Navigate to the Integrations section
Click "Add MCP Server"
Copy and paste the configuration below based on your operating system

Note: Make sure to restart Cline after adding the configuration.

JSON

{
    "mcpServers": {
        "\ud83e\udde0 mcp code assistant": {
            "mcp-server-kiranimmadi2": {
                "command": "python",
                "args": [
                    "mcp.py",
                    "/path/to/your/project",
                    "[options]"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "\ud83e\udde0 mcp code assistant": {
            "mcp-server-kiranimmadi2": {
                "command": "python",
                "args": [
                    "mcp.py",
                    "/path/to/your/project",
                    "[options]"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "\ud83e\udde0 mcp code assistant": {
            "mcp-server-kiranimmadi2": {
                "command": "python",
                "args": [
                    "mcp.py",
                    "/path/to/your/project",
                    "[options]"
                ]
            }
        }
    }
}

Setting up with Goose

Open Goose's preferences
Go to the Integrations tab
Select "MCP Servers"
Click "Add New Server"
Use the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "\ud83e\udde0 mcp code assistant": {
            "mcp-server-kiranimmadi2": {
                "command": "python",
                "args": [
                    "mcp.py",
                    "/path/to/your/project",
                    "[options]"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "\ud83e\udde0 mcp code assistant": {
            "mcp-server-kiranimmadi2": {
                "command": "python",
                "args": [
                    "mcp.py",
                    "/path/to/your/project",
                    "[options]"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "\ud83e\udde0 mcp code assistant": {
            "mcp-server-kiranimmadi2": {
                "command": "python",
                "args": [
                    "mcp.py",
                    "/path/to/your/project",
                    "[options]"
                ]
            }
        }
    }
}

From the repository

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.

Claude Desktop / Cursor

Paste into your MCP client config file to install this server.

{
    "mcpServers": {
        "\ud83e\udde0 mcp code assistant": {
            "mcp-server-kiranimmadi2": {
                "command": "python",
                "args": [
                    "mcp.py",
                    "/path/to/your/project",
                    "[options]"
                ]
            }
        }
    }
}

McpServers

{
    "mcp-server-kiranimmadi2": {
        "command": "python",
        "args": [
            "mcp.py",
            "/path/to/your/project",
            "[options]"
        ]
    }
}

🧠 MCP-Based AI Code Analysis Tool

An AI-powered developer tool built on the Model Context Protocol (MCP) that 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

MCP-Based AI Code Analysis Tool bridges the gap between LLM agents and real codebases. It exposes project structure, file contents, class/function maps, and bug detection as structured MCP-compatible tool calls — allowing AI agents (Claude, GPT-4, etc.) to reason about and navigate codebases without manual context injection.

Key capabilities:
- 🔗 MCP Tool Integration: Exposes codebase operations as structured tools consumable by LLM agents
- 🔍 Project Scanning: Maps your entire project structure and identifies all code files
- 🧠 Code Analysis: Extracts classes, functions, imports, and global variables from Python files
- 🔎 Pattern Searching: Searches your entire codebase for specific patterns using regex
- 🐛 Bug Detection: Identifies common Python bugs and anti-patterns
- 📁 File Management: Updates file content programmatically

---

📋 Requirements

Python 3.6 or higher — No external libraries required (uses only Python standard library)

---

🔧 Installation

git clone https://github.com/kiranimmadi2/MCP-Server.git
cd MCP-Server

---

📚 Usage

Command Line Interface

python mcp.py /path/to/your/project [options]

| Option | Description |
|--------|-------------|
| --scan | Scan the project directory |
| --structure | Print the project structure |
| --analyze <file> | Analyze a specific Python file |
| --search <regex> | Search for a regex pattern in code |
| --bugs | Find potential bugs in Python files |

Examples

# Scan and show structure
python mcp.py /path/to/project --scan --structure
Analyze a file
python mcp.py /path/to/project --analyze path/to/file.py
Find bugs
python mcp.py /path/to/project --bugs

---

🧩 Using as a Python Library / MCP Tool Backend

from mcp import MCP
mcp = MCP("/path/to/your/project")

mcp.scan_project()

mcp.print_structure()
Structured output for LLM consumption
analysis = mcp.analyze_python_file("path/to/file.py")
results = mcp.search_code(r"class\s+[A-Z][a-zA-Z0-9_]")
bugs = mcp.find_bugs()

---

🛣️ Roadmap

- [ ] Full MCP server mode with JSON-RPC tool registration
- [ ] LLM agent integration examples (Claude + LangChain)
- [ ] Support for JavaScript and TypeScript
- [ ] Code complexity scoring

---

📄 License

MIT License — see the LICENSE file for details.

Built with pure Python. Designed for the AI-native developer workflow.*

No reviews yet — be the first

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.

About

Details

Jump to

Setting up with Highlight

From the repository

Claude Desktop / Cursor

McpServers

🧠 MCP-Based AI Code Analysis Tool

🌟 Overview

📋 Requirements

🔧 Installation

📚 Usage

Command Line Interface

Examples

Analyze a file

Find bugs

🧩 Using as a Python Library / MCP Tool Backend

Structured output for LLM consumption

🛣️ Roadmap

📄 License

Install

More like this

Sentry

Github

Git

GitLab

Context 7

Playwright