Which integrations are available for this server?

Enables static code analysis of GitHub repositories using Joern's Code Property Graph technology, supporting security analysis, code browsing, and dataflow analysis across multiple programming languages. Provides static code analysis capabilities within VS Code through GitHub Copilot integration, enabling security analysis, taint flow detection, and code graph queries.

How do I use CodeBadger Toolkit?

1. Click on "Install Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@CodeBadger Toolkit find taint flows in the current codebase" That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

🦡 codebadger

A containerized Model Context Protocol (MCP) server providing static code analysis using Joern's Code Property Graph (CPG) technology with support for Java, C/C++, JavaScript, Python, Go, Kotlin, C#, Ghidra, Jimple, PHP, Ruby, and Swift.

Prerequisites

Before you begin, make sure you have:

Docker and Docker Compose installed
Python 3.10+ (Python 3.13 recommended)
pip (Python package manager)

To verify your setup:

docker --version docker-compose --version python --version

Quick Start

1. Install Python Dependencies

# Create a virtual environment (optional but recommended) python -m venv venv # Install dependencies pip install -r requirements.txt

2. Start the Docker Services (Joern)

docker compose up -d

This starts:

Joern Server: Static code analysis engine (runs CPG generation and queries)

Verify services are running:

docker compose ps

3. Start the MCP Server

# Start the server python main.py &

The MCP server will be available at http://localhost:4242.

4. Stop All Services

# Stop MCP server (Ctrl+C in terminal) # Stop Docker services docker-compose down # Optional: Clean up everything bash cleanup.sh

Cleanup Script

Use the provided cleanup script to reset your environment:

bash cleanup.sh

This will:

Stop and remove Docker containers
Kill orphaned Joern/MCP processes
Clear Python cache (__pycache__, .pytest_cache)
Optionally clear the playground directory (CPGs and cached codebases)

Integrations

GitHub Copilot Integration

Edit the MCP configuration file for VS Code (GitHub Copilot):

Path:

~/.config/Code/User/mcp.json

Example configuration:

{ "inputs": [], "servers": { "codebadger": { "url": "http://localhost:4242/mcp", "type": "http" } } }

Claude Code Integration

To integrate codebadger into Claude Desktop, edit:

Path:

Claude → Settings → Developer → Edit Config → claude_desktop_config.json

Add the following:

{ "mcpServers": { "codebadger": { "url": "http://localhost:4242/mcp", "type": "http" } } }

Available Tools

Core Tools

Tool	Description
`generate_cpg`	Generate a CPG for a codebase (from local path or GitHub URL)
`get_cpg_status`	Get status and existence of a CPG by `codebase_hash`
`run_cpgql_query`	Execute raw CPGQL queries
`get_cpgql_syntax_help`	Get CPGQL syntax documentation and examples

Code Browsing Tools

Tool	Description
`get_codebase_summary`	Get high-level codebase overview (files, methods, calls)
`list_files`	List source files in the codebase
`list_methods`	Discover methods/functions with optional filtering
`list_calls`	Find function call relationships
`list_parameters`	Get parameter information for a method
`get_method_source`	Retrieve method source code
`get_code_snippet`	Retrieve code snippets by file and line range
`get_call_graph`	Build call graphs (incoming/outgoing)

Semantic Analysis Tools

Tool	Description
`get_cfg`	Get control flow graph (nodes AND edges) for a method
`get_type_definition`	Get struct/type definition with members
`get_macro_expansion`	Detect potential macro calls using heuristics

Taint Analysis Tools

Tool	Description
`find_taint_sources`	Locate external input points (getenv, malloc, read, etc.)
`find_taint_sinks`	Locate dangerous sinks (memcpy, system, free, etc.)
`find_taint_flows`	Find dataflow paths (source→sink, source-only, or sink-only)
`get_variable_flow`	Track variable assignments and data dependencies

Advanced Analysis Tools

Tool	Description
`get_program_slice`	Build backward program slices from a call
`find_bounds_checks`	Find bounds checks near buffer accesses

Contributing & Tests

Thanks for contributing! Here's a quick guide to get started with running tests and contributing code.

Prerequisites

Python 3.10+ (3.13 is used in CI)
Docker and Docker Compose (for integration tests)

Local Development Setup

Create a virtual environment and install dependencies

python -m venv venv pip install -r requirements.txt

Start Docker services (for integration tests)

docker-compose up -d

Run unit tests

pytest tests/ -q

Run integration tests (requires Docker Compose running)

# Start MCP server in background python main.py & # Run integration tests pytest tests/integration -q # Stop MCP server pkill -f "python main.py"

Run all tests

pytest tests/ -q

Cleanup after testing

bash cleanup.sh docker-compose down

Code Contributions

Please follow these guidelines when contributing:

Follow repository conventions
Write tests for behavioral changes
Ensure all tests pass before submitting PR
Include a clear changelog in your PR description
Update documentation if needed

Configuration

The MCP server can be configured via environment variables or config.yaml.

Environment Variables

Key settings (optional - defaults shown):

# Server MCP_HOST=0.0.0.0 MCP_PORT=4242 # Joern JOERN_BINARY_PATH=joern JOERN_JAVA_OPTS="-Xmx4G -Xms2G -XX:+UseG1GC -Dfile.encoding=UTF-8" # CPG Generation CPG_GENERATION_TIMEOUT=600 MAX_REPO_SIZE_MB=500 # Query QUERY_TIMEOUT=30 QUERY_CACHE_ENABLED=true QUERY_CACHE_TTL=300

Config File

Create a config.yaml from config.example.yaml:

cp config.example.yaml config.yaml

Then customize as needed.

This server cannot be installed

-

security - not tested

A

license - permissive license

-

quality - not tested

How are these scores calculated?

Resources

GitHub Repository

Need Help?

Report Issue

Related Servers

CodeBadger Toolkit

🦡 codebadger

Prerequisites

Quick Start

1. Install Python Dependencies

2. Start the Docker Services (Joern)

3. Start the MCP Server

4. Stop All Services

Cleanup Script

Integrations

GitHub Copilot Integration

Claude Code Integration

Available Tools

Core Tools

Code Browsing Tools

Semantic Analysis Tools

Taint Analysis Tools

Advanced Analysis Tools

Contributing & Tests

Prerequisites

Local Development Setup

Code Contributions

Configuration

Environment Variables

Config File

Resources

New MCP Servers

Latest Blog Posts

MCP directory API