convez.ai
MCP ServerSegurançaAvançado
Lekssays

codebadger - Análise de Código via Graph de Propriedades

Lekssays/codebadger

Análise de código e vulnerabilidades via CPG para agentes IA

Ver no GitHub
BomPluginScore · de 0 a 100

MCP server containerizado que oferece acesso profundo e consultável à estrutura e fluxo de dados de codebases através de Joern Code Property Graphs (CPGs). Suporta análise de programas e busca de vulnerabilidades em 12+ linguagens, com capacidade de executar queries CPGQL, rastreamento de taint e slicing de programas.

Instalação

$npx convez-ai Lekssays/codebadger

1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.

Métricas

Estrelas
183
Forks
25
Acompanhando
2
Saúde
71%
Último commit
há 2 meses
Versão
v0.7.0-beta
Issues abertas
0
Contribuidores
2

Casos de uso

  • Análise de estrutura e fluxo de dados em codebases grandes
  • Detecção e rastreamento de vulnerabilidades e taint tracking
  • Pesquisa acadêmica em análise de programas e segurança
  • Desenvolvimento de detectors customizados para padrões de código

Veredito

Ferramenta robusta e bem documentada para análise profunda de segurança e estrutura de código via LLMs. Ideal para pesquisadores e times de segurança que precisam de capacidades avançadas de program analysis integradas a agentes IA.

README

A tradução para o português deste README ainda está na fila.

🦡 codebadger

codebadger is a containerized Model Context Protocol (MCP) server that gives AI agents and LLMs deep, queryable access to a codebase's structure and data flow through Joern Code Property Graphs (CPGs).

Point it at a Git repository, a local path, or even a pasted code snippet, and codebadger builds a CPG and exposes it over MCP — so an assistant can run CPGQL queries, trace data flow and taint, slice programs, and hunt for vulnerabilities across Java, C/C++, JavaScript, Python, Go, Kotlin, C#, Ghidra, Jimple, PHP, Ruby, and Swift.

It's a general-purpose foundation for both program analysis (understanding code structure, call graphs, and data flow) and vulnerability analysis (taint tracking, bug hunting, and PoC development) — useful for academic research as well as industry security and engineering work. It's built to scale to large analysis batches with per-CPG worker pools, memory-aware scheduling, and a Postgres/Redis backend.

News

codebadger and its paper - Bridging Code Property Graphs and Language Models for Program Analysis - were accepted at the Software Vulnerability Management Workshop @ ICSE 2026. 🎉

Documentation

Everything a developer or security researcher needs lives in docs/:

DocWhat's in it
InstallationPrerequisites and a 5-minute local setup.
UsageConnecting MCP clients, the tool catalog, and a researcher workflow.
Available ToolsEvery MCP tool by category, with a description of what each does.
Configurationconfig.yaml / env reference, telemetry.
DeploymentPostgres/Redis, memory sizing, shared vs pool, large batches.
ArchitectureSystem design and diagrams.
SecurityThreat model, trust boundaries, and production hardening.
Custom ToolsAdd your own detectors.
ContributingDev setup, tests, and guidelines.
RoadmapWhat's shipped and what's next.

Found a vulnerability using codebadger?

We'd love to hear about it - open a PR adding it to TROPHIES.md (CVE ID, project, one-line description, date).

Citation

@inproceedings{lekssays2026bridging,
  title={Bridging Code Property Graphs and Language Models for Program Analysis},
  author={Lekssays, Ahmed},
  booktitle={Proceedings of the 2026 IEEE/ACM 4th International Workshop on Software Vulnerability Management},
  pages={33--40},
  year={2026}
}
Ver o original no GitHub

Bom para

Relacionados