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.
🦡 codebadger-toolkit
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.
Quick Start
Build and Run the Container
The MCP server will be available at http://localhost:4242.
Stop the Service
Integrations
GitHub Copilot Integration
Edit the MCP configuration file for VS Code (GitHub Copilot):
Path:
Example configuration:
Claude Code Integration
To integrate codebadger-toolkit into Claude Desktop, edit:
Path:
Add the following:
Available Tools
Core Tools (hash-based)
generate_cpg: Generate a CPG for a codebase (from local path or GitHub URL)get_cpg_status: Get status and existence of a CPG bycodebase_hashrun_cpgql_query: Execute CPGQL queries (synchronous)
Code Browsing Tools
get_codebase_summary: Get codebase overviewlist_files: List source fileslist_methods: Discover methods/functionsget_method_source: Retrieve method source codelist_calls: Find function call relationshipsget_call_graph: Build call graphslist_parameters: Get parameter informationfind_literals: Search for hardcoded valuesget_code_snippet: Retrieve code snippets
Security Analysis Tools
find_taint_sources: Locate external input pointsfind_taint_sinks: Locate dangerous sinksfind_taint_flows: Find dataflow pathsfind_argument_flows: Find expression reusecheck_method_reachability: Check call graph connectionslist_taint_paths: List detailed taint pathsget_program_slice: Build program slices
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
Create a virtual environment and install dependencies
Run unit tests
Run integration tests (requires Docker Compose)
Run all tests
Please follow the repository conventions and open a PR with a clear changelog and tests for changes that affect behavior.
Configuration
Optional configuration via config.yaml (copy from config.example.yaml).
Key settings:
Server host/port
Redis settings
Session timeouts
CPG generation settings
This server cannot be installed