Lanalyzer MCP Server

Lanalyzer

Lanalyzer is an advanced Python static taint analysis tool designed to detect potential security vulnerabilities in Python projects. It identifies data flows from untrusted sources (Sources) to sensitive operations (Sinks) and provides detailed insights into potential risks.

📖 Table of Contents

Lanalyzer

✨ Features

Taint Analysis: Tracks data flows from sources to sinks.
Customizable Rules: Define your own sources, sinks, sanitizers, and taint propagation paths.
Static Analysis: No need to execute the code.
Extensibility: Easily add new rules for detecting vulnerabilities like SQL Injection, XSS, and more.
Detailed Reports: Generate comprehensive analysis reports with vulnerability details and mitigation suggestions.
Command-Line Interface: Run analyses directly from the terminal.

🚀 Getting Started

Prerequisites

Python 3.10 or higher
uv (recommended for dependency management)

Installation

Option 1: Install from PyPI (Recommended)

# Using pip
pip install lanalyzer

# Install as a tool (recommended)
uv tool install lanalyzer

# Using uv
uv add lanalyzer

# With MCP support
uv add lanalyzer[mcp]

Option 2: Install from Source

git clone https://github.com/bayuncao/lanalyzer.git
cd lanalyzer
uv sync

💻 Usage

Basic Analysis

Run a taint analysis on a Python file:

lanalyzer --target <target_file> --config <config_file> --pretty --output <output_file> --log-file <log_file> --debug --minimal-output

Command-Line Options

--target: Path to the Python file or directory to analyze.
--config: Path to the configuration file.
--output: Path to save the analysis report.
--log-file: Path to save the log file.
--pretty: Pretty-print the output.
--detailed: Show detailed analysis statistics.
--debug: Enable debug mode with detailed logging.
--minimal-output: (Recommended)Output only vulnerabilities and call_chains fields. Default is full output including summary and imports.

Example

lanalyzer --target example.py --config rules/sql_injection.json --pretty --output example_analysis.json --log-file example_analysis.log --debug

🤝 Contributing

We welcome contributions! Please see the CONTRIBUTING.md file for guidelines on how to contribute to Lanalyzer.

For development setup, building, and publishing instructions, see DEVELOPMENT.md.

📄 License

This project is licensed under the GNU Affero General Public License v3.0. See the LICENSE file for details.

📞 Contact

Contact

Issues: GitHub Issues
Email: 8533596#gmail.com

🧩 Model Context Protocol (MCP) Support

Lanalyzer now supports the Model Context Protocol (MCP), allowing it to run as an MCP server that AI models and tools can use to access taint analysis functionality through a standard interface.

Installing MCP Dependencies

If you're using pip:

pip install "lanalyzer[mcp]"

If you're using uv:

uv add lanalyzer[mcp]

Starting the MCP Server

There are multiple ways to start the MCP server:

Using Python Module:

# View help information
python -m lanalyzer.mcp --help

# Start the server (default port 8001)
python -m lanalyzer.mcp run --port 8001 --debug

Using the lanalyzer Command-Line Tool:

# View help information
lanalyzer mcp --help

# Start the server (default port 8000)
lanalyzer mcp run --port 8000 --debug

# Use development mode
lanalyzer mcp dev

MCP Server Features

The MCP server provides comprehensive security analysis capabilities through 8 specialized tools:

Core Analysis Tools

analyze_code - Analyze Python code strings for security vulnerabilities
- Performs static taint analysis on provided Python source code
- Detects SQL injection, command injection, path traversal, and other security issues
- Returns detailed vulnerability reports with call chains and import information
analyze_file - Analyze individual Python files for security vulnerabilities
- Reads and analyzes Python source files from the filesystem
- Provides the same comprehensive analysis as analyze_code but for file-based input
- Supports minimal output mode for focused vulnerability reporting
analyze_path - Analyze files or directories for security vulnerabilities
- Recursively processes entire directories or single files
- Provides comprehensive security analysis reports for projects
- Aggregates results across multiple files with summary statistics

Configuration Management Tools

get_config - Retrieve Lanalyzer configuration content
- Returns current configuration settings or default configuration
- Allows examination of detection rules and analysis settings
- Supports both file-based and default configuration retrieval
validate_config - Validate configuration data for correctness
- Checks configuration structure, required fields, and data types
- Validates both direct configuration data and configuration files
- Returns detailed validation errors and warnings
create_config - Create new configuration files
- Generates new Lanalyzer configuration files with specified settings
- Validates configuration before creation to ensure correctness
- Supports custom detection rules and analysis parameters

Report Generation Tools

explain_vulnerabilities - Generate natural language explanations
- Converts technical vulnerability analysis into human-readable explanations
- Supports both brief summaries and detailed explanations with remediation
- Output formats: plain text or Markdown
write_vulnerability_report - Generate standardized vulnerability reports
- Creates professional vulnerability reports in CVE or CNVD formats
- Supports comprehensive vulnerability documentation with CVSS scoring
- Includes metadata, affected products, and remediation information

For detailed MCP API documentation, see MCP Tools Reference.

Using Lanalyzer in the MCP client

`Cursor`	`Augment`	`CherryStudio`

Integration with AI Tools

The MCP server can be integrated with AI tools that support the MCP protocol:

# Using the FastMCP client
from fastmcp import FastMCPClient

# Create a client connected to the server
client = FastMCPClient("http://127.0.0.1:8000")

# Analyze code
result = client.call({
    "type": "analyze_code",
    "code": "user_input = input()\nquery = f\"SELECT * FROM users WHERE name = '{user_input}'\"",
    "file_path": "example.py",
    "config_path": "/path/to/config.json"
})

# Print analysis results
print(result)

Using in Cursor

If you're working in the Cursor editor, you can directly ask the AI to use Lanalyzer to analyze your code:

Please use lanalyzer to analyze the current file for security vulnerabilities and explain the potential risks.

MCP Command-Line Options

The MCP server supports the following command-line options:

For python -m lanalyzer.mcp run:

--debug: Enable debug mode with detailed logging
--host: Set the server listening address (default: 127.0.0.1)
--port: Set the server listening port (default: 8001)
--transport: Transport protocol (sse or streamable-http)

For lanalyzer mcp run:

--debug: Enable debug mode
--port: Set the server listening port (default: 8000)

Advanced MCP Usage

Custom Configurations

You can use the get_config, validate_config, and create_config tools to manage vulnerability detection configurations:

# Get the default configuration
config = client.call({
    "type": "get_config"
})

# Create a new configuration
result = client.call({
    "type": "create_config",
    "config_data": {...},  # Configuration data
    "config_path": "/path/to/save/config.json"  # Optional
})

Batch File Analysis

Analyze an entire project or directory:

result = client.call({
    "type": "analyze_path",
    "target_path": "/path/to/project",
    "config_path": "/path/to/config.json",
    "output_path": "/path/to/output.json"  # Optional
})

📊 Analysis Results Format

The analysis results are returned in JSON format with the following main sections:

vulnerabilities: List of detected security vulnerabilities
call_chains: Data flow paths from sources to sinks
summary: Analysis statistics and overview
imports: Import information for analyzed files

For detailed format specification, see Output Format Documentation.

This server cannot be installed

security - not tested

license - permissive license

quality - not tested

How are these scores calculated?

remote-capable server

The server can be hosted and run remotely because it primarily relies on remote services or has no dependency on the local environment.

Provides Python code security analysis through the Model Context Protocol, enabling AI tools to detect potential vulnerabilities like SQL injection and XSS by identifying tainted data flows from untrusted sources to sensitive operations.

Related MCP Servers

Argus
athapong
-
security
A
license
-
quality
A Model Context Protocol tool for analyzing code repositories, performing security scans, and assessing code quality across multiple programming languages.
Last updated -
1
Python
MIT License
Python MCP Server
hesiod-au
-
security
A
license
-
quality
A Model Context Protocol server that extracts and analyzes Python code structures, focusing on import/export relationships between files to help LLMs understand code context.
Last updated -
6
Python
MIT License
ExploitDB MCP Server
Cyreslab-AI
-
security
A
license
-
quality
A Model Context Protocol server that enables AI assistants to search and retrieve information about security exploits and vulnerabilities from the Exploit Database, enhancing cybersecurity research capabilities.
Last updated -
9
TypeScript
MIT License
CodeAnalysis MCP Server
0xjcf
A
security
F
license
A
quality
A comprehensive Model Context Protocol server for advanced code analysis that provides tools for syntax analysis, dependency visualization, and AI-assisted development workflow support.
Last updated -
28
4
Python

View all related MCP servers

Appeared in Searches

A server that scans projects for security vulnerabilities and recommends fixes