Skip to main content
Glama
neurodev-mcp

neurodev-mcp

by ravikant1918

🧠 NeuroDev MCP Server

Intelligent Code Analysis, Test Generation & Execution

Python 3.8+ MCP License: MIT Tests

A powerful Model Context Protocol (MCP) server that supercharges your Python development workflow with AI-powered code review, intelligent test generation, and comprehensive test execution.

Features β€’ Installation β€’ Quick Start β€’ Tools β€’ Examples


✨ Features

πŸ” Code Review

  • 6 Powerful Analyzers

    • pylint - Code quality & PEP8

    • flake8 - Style enforcement

    • mypy - Type checking

    • bandit - Security scanning

    • radon - Complexity metrics

    • AST - Custom inspections

  • Real-time issue detection

  • Security vulnerability scanning

  • Complexity & maintainability scores

πŸ§ͺ Test Generation

  • Intelligent AST Analysis

    • Auto-generate pytest tests

    • Happy path coverage

    • Edge case handling

    • Exception testing

    • Type validation tests

  • Supports functions & classes

  • Type-hint aware

▢️ Test Execution

  • Comprehensive Testing

    • Isolated environment

    • Coverage reporting

    • Line-by-line analysis

    • Timeout protection

  • Detailed pass/fail results

  • Performance metrics

🎨 Code Formatting

  • Auto-formatting

    • black - Opinionated style

    • autopep8 - PEP8 compliance

  • Configurable line length

  • Consistent code style

  • One-command formatting


Related MCP server: Moatless MCP Server

πŸ“¦ Installation

Quick Install

```bash

# Clone the repository
git clone https://github.com/ravikant1918/neurodev-mcp.git
cd neurodev-mcp

# Create virtual environment (recommended)
python -m venv .venv
source .venv/bin/activate  # On Windows: .venv\\Scripts\\activate

# Install the package
pip install -e .
\`\`\`

### **Verify Installation**

\`\`\`bash
# Run tests (should show 15/15 passing)
python test_installation.py

# Test the server
python -m neurodev_mcp.server
\`\`\`

<details>
<summary><b>πŸ“ Project Structure</b> (click to expand)</summary>

\`\`\`
neurodev-mcp/
β”œβ”€ neurodev_mcp/              # πŸ“¦ Main package
β”‚   β”œβ”€ __init__.py            # Package exports
β”‚   β”œβ”€ server.py              # MCP server entry point
β”‚   β”œβ”€ analyzers/             # πŸ” Code analysis
β”‚   β”‚   β”œβ”€ __init__.py
β”‚   β”‚   └─ code_analyzer.py   # Multi-tool static analysis
β”‚   β”œβ”€ generators/            # πŸ§ͺ Test generation
β”‚   β”‚   β”œβ”€ __init__.py
β”‚   β”‚   └─ test_generator.py  # AST-based test creation
β”‚   └─ executors/             # ▢️ Test execution
β”‚       β”œβ”€ __init__.py
β”‚       └─ test_executor.py   # Test running & formatting
β”œβ”€ pyproject.toml             # Project configuration
β”œβ”€ README.md                  # This file
β”œβ”€ test_installation.py       # Installation validator
β”œβ”€ examples.py                # Usage examples
└─ requirements.txt           # Dependencies

πŸš€ Quick Start

Step 1: Configure Your MCP Client

Edit ~/Library/Application Support/Claude/claude_desktop_config.json:

{
  "mcpServers": {
    "neurodev-mcp": {
      "command": "/absolute/path/to/neurodev-mcp/.venv/bin/python",
      "args": ["-m", "neurodev_mcp.server"]
    }
  }
}

πŸ’‘ Tip: Replace /absolute/path/to/neurodev-mcp with your actual path

Add to your MCP settings:

{
  "neurodev-mcp": {
    "command": "python",
    "args": ["-m", "neurodev_mcp.server"]
  }
}

Run the server directly:

# Using the module
python -m neurodev_mcp.server

# Or as a command (if installed)
neurodev-mcp

Step 2: Restart Your Client

Restart Claude Desktop or reload VSCode to load the server.

Step 3: Start Using! πŸŽ‰

Try these commands with your AI assistant:

  • "Review this Python code for issues"

  • "Generate unit tests for this function"

  • "Run these tests with coverage"

  • "Format this code to PEP8 standards"


🌐 Transport Options

NeuroDev MCP supports multiple transport protocols for different use cases:

STDIO (Default) - Local CLI

Perfect for local development with MCP clients like Claude Desktop or Cline:

# Default STDIO transport
neurodev-mcp

# Or explicitly specify STDIO
neurodev-mcp --transport stdio

Configuration (Claude Desktop):

{
  "mcpServers": {
    "neurodev-mcp": {
      "command": "neurodev-mcp",
      "args": ["--transport", "stdio"]
    }
  }
}

SSE (Server-Sent Events) - Web Integration

For web-based integrations and HTTP streaming:

# Run with SSE on default port (8000)
neurodev-mcp --transport sse

# Custom host and port
neurodev-mcp --transport sse --host 0.0.0.0 --port 3000

Endpoints:

  • SSE Stream: http://localhost:8000/sse

  • Messages: http://localhost:8000/messages (POST)

Web Client Example:

const sse = new EventSource('http://localhost:8000/sse');

sse.onmessage = (event) => {
  const data = JSON.parse(event.data);
  console.log('Received:', data);
};

// Send message
fetch('http://localhost:8000/messages', {
  method: 'POST',
  headers: { 'Content-Type': 'application/json' },
  body: JSON.stringify({
    method: 'tools/call',
    params: {
      name: 'code_review',
      arguments: { code: 'def test(): pass', analyzers: ['pylint'] }
    }
  })
});

Transport Comparison

Transport

Use Case

Best For

STDIO

Local CLI clients

Claude Desktop, Cline, local development

SSE

Web integrations

Browser apps, webhooks, remote clients


πŸ› οΈ Available Tools

1. code_review

πŸ” Comprehensive code analysis with multiple static analysis tools

Input:

{
  "code": "def calculate(x):\n    return x * 2",
  "analyzers": ["pylint", "flake8", "mypy", "bandit", "radon", "ast"]
}

Output:

  • Detailed issue reports from each analyzer

  • Security vulnerabilities

  • Complexity metrics

  • Code quality scores

  • Line-by-line suggestions


2. generate_tests

πŸ§ͺ Intelligent pytest test generation using AST analysis

Input:

{
  "code": "def add(a: int, b: int) -> int:\n    return a + b",
  "module_name": "calculator",
  "save": false
}

Output:

  • Complete pytest test suite

  • Multiple test cases (happy path, edge cases, exceptions)

  • Type validation tests

  • Ready-to-run test code


3. run_tests

▢️ Execute pytest tests with coverage reporting

Input:

{
  "test_code": "def test_add():\n    assert add(1, 2) == 3",
  "source_code": "def add(a, b):\n    return a + b",
  "timeout": 30
}

Output:

  • Pass/fail status

  • Coverage percentage

  • Line coverage details

  • Execution time

  • Detailed stdout/stderr


4. format_code

🎨 Auto-format Python code to PEP8 standards

Input:

{
  "code": "def   messy(  x,y  ):\n        return x+y",
  "line_length": 88
}

Output:

  • Beautifully formatted code

  • PEP8 compliant

  • Consistent style

  • Change detection


πŸ’‘ Usage Examples

Example 1: Complete Code Review Workflow

You: "Review this code for issues and security problems"

[paste code]

AI: [Uses code_review tool]
    β†’ Finds 3 style issues
    β†’ Detects 1 security vulnerability
    β†’ Suggests complexity improvements
    
You: "Fix those issues and show me the updated code"

AI: [Provides fixed code with explanations]

Example 2: Test Generation & Execution

You: "Generate tests for this function and run them"

def divide(a: float, b: float) -> float:
    if b == 0:
        raise ValueError("Cannot divide by zero")
    return a / b

AI: [Uses generate_tests tool]
    β†’ Creates 5 test cases
    β†’ Includes edge cases (zero, negative numbers)
    β†’ Tests exception handling
    
    [Uses run_tests tool]
    β†’ 5/5 tests passing βœ“
    β†’ 100% code coverage
    β†’ All edge cases handled

Example 3: Code Formatting

You: "Format this messy code"

def   calculate(  x,y,z  ):
        result=x+y+z
        if result>10:
                    return   True
        return False

AI: [Uses format_code tool]
    β†’ Applies black formatting
    β†’ Returns clean, PEP8-compliant code

def calculate(x, y, z):
    result = x + y + z
    if result > 10:
        return True
    return False

πŸ“‹ Requirements

Package

Version

Purpose

mcp

β‰₯0.9.0

Model Context Protocol SDK

pylint

β‰₯3.0.0

Code quality analysis

flake8

β‰₯7.0.0

Style checking

mypy

β‰₯1.7.0

Static type checking

bandit

β‰₯1.7.5

Security scanning

radon

β‰₯6.0.1

Complexity metrics

black

β‰₯23.12.0

Code formatting

autopep8

β‰₯2.0.4

PEP8 formatting

pytest

β‰₯7.4.3

Testing framework

pytest-cov

β‰₯4.1.0

Coverage reporting

pytest-timeout

β‰₯2.2.0

Test timeouts

Python: 3.8 or higher


πŸ§ͺ Development

Running Tests

# Run installation tests
python test_installation.py

# Run examples
python examples.py

# Run pytest (if you add tests)
pytest

Using as a Library

from neurodev_mcp import CodeAnalyzer, TestGenerator, TestExecutor
import asyncio

# Analyze code
code = "def hello(): print('world')"
result = asyncio.run(CodeAnalyzer.analyze_ast(code))

# Generate tests
tests = TestGenerator.generate_tests(code, "mymodule")

# Run tests
output = TestExecutor.run_tests(test_code, source_code)

❓ Troubleshooting

  • βœ… Check that the path in config is absolute

  • βœ… Ensure the Python executable path is correct

  • βœ… Restart Claude Desktop or VSCode completely

  • βœ… Check server logs for errors

# Reinstall the package
pip install -e .

# Verify installation
python -c "from neurodev_mcp import CodeAnalyzer; print('βœ“ OK')"

# Run installation tests
python test_installation.py
  • βœ… Ensure Python 3.8+ is installed

  • βœ… Activate virtual environment: source .venv/bin/activate

  • βœ… Reinstall dependencies: pip install -e .

  • βœ… Run: python test_installation.py to diagnose

  • Some analyzers (pylint, mypy) can be slow on large files

  • Use specific analyzers: "analyzers": ["flake8", "ast"]

  • Increase timeout for large test suites

  • Consider caching results (future feature)


🀝 Contributing

Contributions are welcome! Here's how:

  1. Fork the repository

  2. Create a feature branch: git checkout -b feature/amazing-feature

  3. Make your changes

  4. Run tests: python test_installation.py

  5. Commit: git commit -m 'Add amazing feature'

  6. Push: git push origin feature/amazing-feature

  7. Open a Pull Request

Future Enhancements

  • Additional analyzers (pydocstyle, vulture)

  • Result caching for performance

  • Configuration file support

  • Web dashboard

  • Multi-language support

  • CI/CD pipeline


πŸ“„ License

This project is licensed under the MIT License - see the LICENSE file for details.


πŸ™ Acknowledgments


πŸ“ž Support


Ready to supercharge your Python development! πŸš€

Made with ❀️ by the NeuroDev Team

⭐ Star on GitHub β€’ πŸ› Report Bug β€’ ✨ Request Feature

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      F
      maintenance
      A Model Context Protocol server that enables AI assistants like Claude to perform Python development tasks through file operations, code analysis, project management, and safe code execution.
      9
      MIT
    • F
      license
      Not graded
      quality
      D
      maintenance
      A universal AI assistant MCP server that transforms Claude into a multi-talented development assistant with intelligent mode selection, conversation continuity, and smart file handling. Automatically adapts to different tasks like debugging, code analysis, planning, and testing while supporting multiple AI providers and maintaining context across conversations.
      11
      -
    • A
      license
      A
      quality
      B
      maintenance
      An extensible MCP server that provides intelligent Python code analysis, navigation, and understanding capabilities for AI assistants like Claude.
      22
      139 PyPI
      1
      MIT