</>MCP Agents Market
Plugin

raptor

by gadievron3.7kPythonUpdated 2026-08-31

Raptor turns Claude Code into a general-purpose AI offensive/defensive security agent. By using Claude.md and creating rules, sub-agents, and skills, and orchestrating security tool usage, we configure the agent for adversarial thinking, and perform research or attack/defense operations.

Claude Code

RAPTOR is a Claude Code plugin that converts Claude Code into a comprehensive offensive and defensive security research agent. Built on Claude Code's architecture, it orchestrates static analysis tools (Semgrep, CodeQL, Coccinelle), binary analysis, fuzzing, and LLM-powered vulnerability validation into automated security workflows. The plugin adds specialized slash commands, adversarial thinking personas, and multi-stage exploit validation pipelines that enable autonomous vulnerability discovery, exploit generation, and patch creation across codebases and binaries.

Key Features

Autonomous security pipeline with /agentic command for full scan-validate-exploit-patch workflow
Multi-stage exploitability validation (Stages A-F) using LLM analysis to filter false positives
Static analysis integration with 200+ custom Semgrep, Coccinelle, and CodeQL rules plus registry packs
Binary analysis with evidence-based investigation, radare2/Ghidra integration, and runtime tracing via Frida
Software composition analysis (SCA) with dependency mapping, OSV/CISA KEV advisories, SBOM generation, and supply-chain risk signals
Z3 SMT solver integration for dataflow path satisfiability and one-gadget constraint analysis
Multi-model LLM support with separate orchestration (Claude Code) and analysis dispatch layers
Project workspaces with merged findings, coverage tracking, and run-to-run diff comparison

Use Cases

  • 01Autonomous vulnerability discovery in source code repositories using combined static analysis and LLM validation
  • 02Binary exploitation research with evidence-backed reverse engineering and runtime instrumentation
  • 03Security code review with systematic hypothesis-driven audit workflows and coverage tracking
  • 04Supply chain security assessment with dependency analysis, vulnerability enrichment, and automated fix proposals
  • 05Exploit proof-of-concept generation and secure patch development for confirmed vulnerabilities
  • 06Fuzzing campaign automation with AFL++ integration and autonomous crash root-cause analysis

Related Plugins

View more

andrej-karpathy-skills

A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.

Plugin216.1k

claude-mem

Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More

Plugin95k

Understand-Anything

Graphs that teach > graphs that impress. Turn any code into an interactive knowledge graph you can explore, search, and ask questions about. Works with Claude Code, Codex, Cursor, Copilot, Gemini CLI, and more.

Plugin84.9k

rtk

CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies

Plugin82.1k

raptor — FAQ

What is RAPTOR?+

RAPTOR is a Claude Code plugin that turns Claude Code into an autonomous security research framework. It adds specialized commands, skills, and agents for vulnerability analysis, binary reverse engineering, and offensive/defensive security operations.

How do I install RAPTOR?+

Clone the repository, install Python 3.10+ and Node.js 18+ dependencies including Semgrep, then run the raptor launcher script. The recommended approach is using the included Docker container with pre-installed security tooling.

What are the prerequisites?+

Requires Claude Code with an active subscription (Max, Pro, Team, or Enterprise) or Anthropic API key, Python 3.10+, Node.js 18+, and Semgrep. Optional tools include CodeQL, Z3 solver, and Google Cloud credentials for OSS forensics BigQuery access.

Does RAPTOR work with other AI clients besides Claude Code?+

RAPTOR is built specifically for Claude Code as the orchestration layer. The analysis dispatch layer supports multiple LLM providers (Anthropic, OpenAI, Gemini, Mistral, Ollama) but the command framework requires Claude Code.

Is RAPTOR free to use?+

RAPTOR itself is MIT licensed and free. However, you need a Claude Code subscription for orchestration, and analysis-layer LLM calls may incur API costs depending on which models you configure (default uses Claude Code subscription with no extra cost).

Can RAPTOR run offline or in air-gapped environments?+

Yes, RAPTOR's custom static analysis rules run fully offline. Registry packs can be pre-cached using the included cache tool and transferred as zip bundles for air-gapped deployments.

How do I install raptor?+

Open the source repository on GitHub and follow its README. raptor is a plugin — MCP Agents Market links you directly to the official repo.

Is raptor free?+

raptor is an open-source project hosted on GitHub. Check the repository for its license and any usage requirements.

Related searches

Security PluginsDeveloper Tools PluginsCode Review PluginsBest MCP ServersBest SkillsBest AgentsTop rated listingsClaude Code toolsBrowse all categories