Farofino MCP Server
Enables smart contract security auditing using Slither, Aderyn, and custom pattern analysis through the Model Context Protocol, allowing AI assistants to run static analysis and vulnerability checks on Solidity and Vyper contracts.
README
Faro Fino - Smart Contract Audit MCP Server
A Model Context Protocol (MCP) server for auditing smart contracts using industry-standard tools like Slither, Aderyn, and custom pattern analysis.
Overview
This MCP server provides a unified interface for running multiple smart contract security analysis tools through the Model Context Protocol. It enables AI assistants and other MCP clients to perform comprehensive security audits on Solidity and Vyper smart contracts.
Features
- Slither Integration: Static analysis framework for Solidity & Vyper
- Aderyn Integration: Rust-based static analyzer for Solidity
- Pattern Analysis: Custom pattern-based security checks for common vulnerabilities
- Contract Reading: Read and inspect contract source code
- Tool Management: Check which audit tools are installed and get installation instructions
Installation
Option 1: Docker (Recommended - All Tools Pre-installed)
Use Docker for a hassle-free setup with all audit tools pre-installed:
# Clone the repository
git clone https://github.com/italoag/farofino-mcp.git
cd farofino-mcp
# Build and run with Docker Compose
docker-compose build
docker-compose run --rm farofino-mcp
If you encounter network timeout errors during build, see DOCKER_NETWORK_TIMEOUT.md for quick fixes or use:
make build-retry # Automatically handles network issues
Advantages:
- Aderyn and Slither pre-installed
- Consistent environment across all platforms
- No dependency conflicts
- Optimized slim image (~1.3-1.4GB)
See DOCKER.md for detailed Docker setup and configuration.
Option 2: pip Installation
Prerequisites
- Python 3.9 or higher
- pip
Install the MCP Server
pip install farofino-mcp
Or install locally from source:
git clone https://github.com/italoag/farofino-mcp.git
cd farofino-mcp
pip install -r requirements.txt
pip install -e .
Install Audit Tools (Optional)
The server works with various external audit tools. Install the ones you need:
Slither:
pip install slither-analyzer
Aderyn: (via Cyfrinup)
curl -LsSf https://raw.githubusercontent.com/Cyfrin/up/main/install | bash
CYFRINUP_ONLY_INSTALL=aderyn cyfrinup
You can check which tools are installed using the check_tools command.
Usage
With Docker
# Using Docker Compose
docker-compose run --rm farofino-mcp
# Or with Docker directly
docker run -i --rm -v $(pwd)/contracts:/contracts:ro farofino-mcp:latest
See DOCKER.md for detailed Docker usage and configuration.
Without Docker
Running the Server
python3 -m farofino_mcp
Or if installed as a package:
farofino-mcp
Available Tools
1. slither_audit
Run Slither static analysis on a smart contract.
Parameters:
contract_path(required): Path to the contract file (.sol or .vy)detectors(optional): Comma-separated list of specific detectors to runexclude_detectors(optional): Comma-separated list of detectors to exclude
Example: (replace /path/to/MyContract.sol with your actual file path)
{
"contract_path": "/path/to/MyContract.sol",
"detectors": "reentrancy-eth,unchecked-transfer"
}
2. aderyn_audit
Run Aderyn static analysis on a smart contract.
Parameters:
contract_path(required): Path to the contract file or project root
Example: (replace /path/to/MyContract.sol with your actual file path)
{
"contract_path": "/path/to/MyContract.sol"
}
3. pattern_analysis
Perform basic pattern-based security analysis.
Parameters:
contract_path(required): Path to the contract file
Example: (replace /path/to/MyContract.sol with your actual file path)
{
"contract_path": "/path/to/MyContract.sol"
}
Checks for:
selfdestructusagedelegatecallusagetx.originauthentication- Missing SafeMath (pre-0.8.0)
block.timestampmanipulation risks- Potential reentrancy patterns
4. read_contract
Read and return the source code of a smart contract.
Parameters:
contract_path(required): Path to the contract file
Example: (replace /path/to/MyContract.sol with your actual file path)
{
"contract_path": "/path/to/MyContract.sol"
}
5. check_tools
Check which audit tools are installed and available.
Parameters: None
Example:
{}
Returns a list of available and missing tools with installation instructions.
Configuration with Claude Desktop
Add this to your Claude Desktop configuration file:
Configuration File Locations
- macOS:
~/Library/Application Support/Claude/claude_desktop_config.json - Windows:
%APPDATA%/Claude/claude_desktop_config.json - Linux:
~/.config/Claude/claude_desktop_config.json
Option 1: Using Docker (Recommended - All Tools Pre-installed)
{
"mcpServers": {
"farofino": {
"command": "docker",
"args": ["run", "-i", "--rm", "-v", "${PWD}/contracts:/contracts:ro", "farofino-mcp:latest"],
"cwd": "/path/to/farofino-mcp"
}
}
}
Notes:
- Replace
/path/to/farofino-mcpwith the absolute path to this repository on your host machine so Docker sees the right directory. - On Windows, replace
${PWD}with%CD%.
Option 2: Using Docker Compose
{
"mcpServers": {
"farofino": {
"command": "docker-compose",
"args": ["run", "--rm", "farofino-mcp"],
"cwd": "/path/to/farofino-mcp"
}
}
}
Tip: Replace /path/to/farofino-mcp with the absolute host path so docker-compose finds the repo configuration.
Option 3: Using Python Module (No Docker)
{
"mcpServers": {
"farofino": {
"command": "python3",
"args": ["-m", "farofino_mcp"],
"cwd": "/path/to/farofino-mcp"
}
}
}
Tip: Replace the cwd placeholder with the absolute directory where you installed farofino-mcp.
Option 4: Using pip Installation (No Docker)
{
"mcpServers": {
"farofino": {
"command": "farofino-mcp"
}
}
}
For more Docker configuration options, see DOCKER.md.
Example Workflow
Replace /path/to/contract.sol with the actual location of your Solidity file in the steps below.
-
Check available tools:
Use check_tools to see which audit tools are installed -
Read the contract:
Use read_contract with contract_path="/path/to/contract.sol" -
Run pattern analysis (always available):
Use pattern_analysis with contract_path="/path/to/contract.sol" -
Run Slither analysis (if installed):
Use slither_audit with contract_path="/path/to/contract.sol" -
Run additional tools as needed:
- Aderyn for Rust-based analysis (pre-installed in the Docker image or via Cyfrinup)
Development
Building from Source
git clone https://github.com/italoag/farofino-mcp.git
cd farofino-mcp
pip install -r requirements.txt
pip install -e .
Development Mode
# Run directly from source
python3 -m farofino_mcp
# With debugging
python3 -u -m farofino_mcp
Project Structure
farofino-mcp/
├── farofino_mcp/
│ ├── __init__.py # Package initialization
│ └── __main__.py # Main server implementation
├── pyproject.toml # Python project configuration
├── requirements.txt # Python dependencies
├── setup.py # Setup configuration
├── Dockerfile # Docker configuration
└── README.md # This file
Troubleshooting
Tool not found errors
If you get errors about tools not being found:
- Run the
check_toolscommand to see which tools are installed - Install missing tools following the installation instructions above
- Ensure the tools are in your system PATH
Permission errors
If you get permission errors when running audit tools:
- Ensure the contract files are readable
- Check that audit tools have proper execution permissions
Large contracts timing out
For large contracts or complex analysis:
- Use
exclude_detectorswith Slither to skip certain checks - Run pattern analysis first for a quick overview
License
Apache-2.0
Contributing
Contributions are welcome! Please feel free to submit issues or pull requests.
Security
This tool is for educational and professional security auditing purposes. Always:
- Verify audit results manually
- Use multiple tools for comprehensive analysis
- Follow secure development best practices
- Never rely solely on automated tools for security guarantees
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。