// the index

Claude Security Resources & MCPs

Filterable. Searchable. Every entry vetted, sourced, and tagged. No SEO chum, no hallucinated repos.

tool8.7k

PentestGPT

Autonomous penetration testing assistant that drives Claude (and other LLMs) through recon, vuln discovery and exploitation reasoning end-to-end.

#pentest#agent#automation
GreyDGL
tool2.4k

CAI — Cybersecurity AI Framework

Open framework wiring Claude into CTF solving, web exploitation and binary analysis loops with tool-use sandboxes.

#ctf#framework#agent
Alias Robotics
tool1.3k

hackingBuddyGPT

Academic Linux privilege-escalation agent. Drops you on a target box and lets the LLM iterate enumeration → exploit → loot.

#privesc#linux#agent
IPA Lab, TU Wien
tool4.2k

Vulnhuntr

Static analysis agent that uses Claude to find remotely exploitable zero-days in open-source Python projects — has CVEs to its name.

#sast#0day#python
Protect AI
method

Nuclei + Claude Triage Pipeline

Pipes Nuclei scan output into Claude to deduplicate, prioritise and write exploit narratives for bug bounty reports.

#bug-bounty#nuclei#triage
ProjectDiscovery community
tool2.1k

Shennina

Automated exploitation framework that uses an LLM brain to pick Metasploit modules against discovered services.

#metasploit#exploitation#agent
mhaskar
tool2.6k

BurpGPT

Burp Suite extension that ships requests/responses to Claude for traffic-aware vulnerability hypotheses and parameter fuzzing ideas.

#burp#web#fuzzing
aress31
research1.5k

AI Exploits

Collection of real CVEs and PoCs targeting AI/ML supply-chain components — perfect playground for Claude-driven exploit dev.

#ml-security#cve#poc
Protect AI
mcp65k

Model Context Protocol — Reference Servers

Canonical MCP servers (filesystem, git, github, postgres, fetch). Foundation for everything else on this page.

#mcp#tools#agent
Anthropic / MCP
mcp

MCP Nmap Server

Exposes nmap to Claude as a structured tool — full flag surface, safe-mode guards, JSON-typed scan results.

#mcp#recon#nmap
Wh0am123
mcp

Metasploit MCP

Lets Claude search modules, set options, launch handlers and read session output from a live msfrpc instance.

#mcp#metasploit#exploitation
GH05TCREW
mcp5.1k

GhidraMCP

Reverse-engineering MCP that gives Claude function listings, decompiled C and cross-references straight out of Ghidra.

#mcp#reverse-engineering#ghidra
LaurieWired
mcp

Binary Ninja MCP

Same idea for Binary Ninja users — symbol lookup, decompilation, structural analysis driven by Claude.

#mcp#reverse-engineering#binja
MatthewDFT
mcp

Burp Suite MCP

Wires Burp proxy history, scanner findings and Repeater into Claude for end-to-end web-app testing loops.

#mcp#burp#web
PortSwigger
mcp

Shodan MCP

Query Shodan, lookup hosts, run search facets and CVE pivots from inside a Claude conversation.

#mcp#osint#recon
BurtTheCoder
mcp

VirusTotal MCP

Hash, URL and file reputation lookups exposed as MCP tools — ideal for SOC and IR Claude workflows.

#mcp#blue-team#threat-intel
BurtTheCoder
mcp

Wireshark MCP

Exposes pcap parsing, conversation stats and follow-stream to Claude — natural-language packet analysis for IR and CTF forensics.

#mcp#forensics#pcap
0xPraso
mcp

Kali MCP Server

Wraps the Kali toolset (nmap, gobuster, sqlmap, hydra, john) as MCP tools — Claude can drive an entire kill chain end-to-end.

#mcp#kali#offsec
Wh0am123
mcp

Semgrep MCP

Official Semgrep MCP — Claude runs rules, triages findings and writes auto-fix patches inside any IDE.

#mcp#sast#code-audit
Semgrep
mcp

OSV / Dependency MCP

Queries the OSV vulnerability database and lockfiles directly from Claude — instant SBOM-aware vuln triage.

#mcp#sca#vuln-mgmt
StevenStavrakis
tool68k

Gemini CLI

Google's open-source terminal agent for Gemini 2.5/3 Pro — 1M-token context, built-in shell / file / web tools, ReAct loop. Drop-in alternative to Claude Code for recon, code audit and exploit dev.

#cli#agent#gemini
Google
tool

Hermes 4 (Nous Research)

Uncensored open-weights Llama-3.1 405B fine-tune. Strong at offensive security reasoning, exploit narration and tool-use without the refusal tax of frontier models.

#open-weights#uncensored#red-team
Nous Research
tool32k

OpenAI Codex CLI

OpenAI's terminal coding agent (GPT-5 / o-series). Useful counterpart to Claude Code for cross-model security audits and PoC generation.

#cli#agent#gpt
OpenAI
tool38k

Aider

Model-agnostic AI pair-programmer (Claude, GPT-5, Gemini, DeepSeek, local). Great for git-aware code-audit loops and patch generation.

#cli#code-audit#multi-model
Aider-AI
tool23k

OpenCode

Open-source, provider-agnostic terminal coding agent. Plug Claude, Gemini, GPT, Hermes or local models into the same recon/audit workflow.

#cli#agent#open-source
SST
tool52k

Cline

VS Code autonomous coding agent supporting Claude, Gemini, GPT, DeepSeek. Powerful for in-editor exploit prototyping and patch review.

#vscode#agent#multi-model
Cline
tool

Nuclei AI Templates

ProjectDiscovery's AI-assisted Nuclei template generator — describe a vuln in English, get a working template. Pair with Claude for bug-bounty 0-day chasing.

#nuclei#bug-bounty#templates
ProjectDiscovery
tool33k

Fabric

Open-source framework of 200+ vetted prompts (patterns) for security analysis, threat modelling, CVE summarisation, log triage. Pipes into any LLM.

#prompts#framework#cli
Daniel Miessler
research23k

h4cker — AI Security Resources

Omar Santos's massive curated index of offensive AI, defensive AI, red-team labs and learning paths. Updated weekly.

#awesome#index#learning
Omar Santos
method

The Claude Bug Bounty Playbook

How to use Claude Code to triage scope, generate one-shot Nuclei templates, write disclosure narratives and chain low-sev issues into criticals.

#bug-bounty#claude-code#playbook
Intigriti
method

HackerOne — Hacker Powered LLM Security

Field guide from HackerOne on using LLMs in bounty workflows: report writing, payload crafting, prompt-injection class bugs.

#bug-bounty#hackerone#workflow
HackerOne
method

Claude Code for Recon Automation

Drops Claude Code into a recon pipeline: subdomain enum, JS file scraping, secret discovery, then automatic write-up generation.

#claude-code#recon#bug-bounty
Anthropic
method

Anthropic Model Safety Bug Bounty

Official program targeting universal jailbreaks and safety bypasses in Claude. Read scope before testing.

#bug-bounty#jailbreak#official
Anthropic
prompt

Anthropic Prompt Library

Official, vetted system prompts. Includes code review, threat modelling, regex generation and report summarisation prompts.

#prompts#official
Anthropic
prompt5.8k

Awesome Claude Security Prompts

Community-maintained list of battle-tested system prompts for SOC analyst, red team operator, malware analyst and reverse engineer personas.

#prompts#personas#awesome
langgptai
prompt11k

Leaked System Prompts

Public mirror of leaked / disclosed system prompts (including Claude, Cursor, Devin). Goldmine for prompt-injection research.

#prompt-injection#research#leaks
jujumilk3
tool5.6k

garak — LLM Vulnerability Scanner

Nikto-for-LLMs. Probes Claude for prompt injection, data leakage, toxicity, jailbreak susceptibility and encoding attacks.

#llm-security#scanner#red-team
NVIDIA
tool8.4k

promptfoo

Eval and red-team framework. Run hundreds of jailbreak / injection probes against Claude and diff results across model versions.

#eval#red-team#framework
promptfoo
tool3.3k

PyRIT

Microsoft's Python Risk Identification Toolkit for generative AI. Automated red-teaming with orchestrators, scorers, converters.

#red-team#ms#framework
Microsoft / Azure
research650

JailbreakBench

Open benchmark with 100 attacker behaviours used to evaluate Claude, GPT and open-source model robustness.

#benchmark#jailbreak#research
JailbreakBench team
research

Many-Shot Jailbreaking

Anthropic's own research on long-context jailbreaks — required reading for AI red teamers building robust prompt defenses.

#jailbreak#alignment#long-context
Anthropic Research
research

Indirect Prompt Injection in the Wild

Catalog of real-world indirect prompt injection vectors targeting Claude-powered SaaS — and how to defend.

#prompt-injection#defense
Greshake et al.
research

Agent Hijacking Taxonomy

Taxonomy of attack patterns against tool-using agents — applies directly to Claude with MCP servers granting filesystem / shell access.

#agent-security#research#mcp
Debenedetti et al.
article

Reverse Engineering Malware with Claude

Step-by-step methodology for feeding Ghidra decompilations to Claude and getting accurate behavioural analysis without hallucinating IOCs.

#reverse-engineering#malware#ghidra
Embee Research
tool1.5k

Malimite

iOS / macOS malware decompiler with Claude assistance baked in — naming, comments and behaviour summaries from raw Mach-O.

#malware#ios#decompiler
LaurieWired
tool3.2k

Gepetto

IDA Pro plugin that calls Claude to rename functions, explain pseudocode and identify algorithms inside disassembly.

#ida#reverse-engineering#plugin
JusticeRage
method

Sigma Rule Generation with Claude

Method for converting threat reports and Atomic Red Team tests into validated Sigma detection rules using Claude.

#blue-team#detection#sigma
SigmaHQ community
article

DFIR Triage with Claude

Patterns for using Claude to summarise KAPE outputs, timeline EVTX, and produce executive-ready incident summaries.

#dfir#blue-team#ir
SANS DFIR community
article

Claude in the SOC

Production patterns from blue teams running Claude on alert triage, IOC enrichment and analyst-tier-1 augmentation.

#soc#blue-team#production
Anthropic customer stories
method

Claude Code for Security Audits

How to drive Claude Code as a terminal-native auditor: taint flow tracing, sink discovery, PoC exploit generation.

#claude-code#code-audit#sast
Anthropic
method

Semgrep + AI Triage

Pipeline that runs Semgrep, then uses Claude to triage findings, drop false positives and rank by exploitability.

#sast#semgrep#triage
Semgrep community
research

OWASP LLM Top 10 (2025)

Canonical list of LLM vulnerabilities: prompt injection, insecure output handling, supply chain, model DoS, sensitive disclosure.

#owasp#llm-security#standard
OWASP
research

MITRE ATLAS

Adversarial threat matrix for AI systems — tactics, techniques and real-world case studies including LLM agents.

#mitre#threat-model#ai
MITRE
research

Constitutional AI

How Anthropic's Constitutional AI principles translate into building security agents that refuse harmful side-effects.

#alignment#agent#safety
Anthropic
research

MCP Security Best Practices

Official guidance for sandboxing MCP servers, scoping tool surface and preventing prompt-injection-driven tool abuse.

#mcp#agent-security#best-practice
Anthropic / MCP
course12k

Anthropic Skill Courses

Free, official courses on prompt engineering, tool use, real-world prompting and API fundamentals.

#learning#official#free
Anthropic
course

Red-Teaming LLM Applications

DeepLearning.AI short course on red-teaming LLM apps — directly applicable to Claude-backed products.

#course#red-team#learning
DeepLearning.AI
course

PortSwigger Web Security Academy — LLM Attacks

Free labs covering prompt injection, insecure output handling and LLM-driven attacks against web apps.

#learning#labs#web
PortSwigger
research2.3k

Awesome LLM Security

The reference meta-list: tools, papers, datasets, defences, attacks. Update cadence is excellent.

#awesome#meta#index
Corca AI
mcp40k

Awesome MCP Servers

Curated index of MCP servers — over 500 entries spanning recon, exploitation, OSINT, dev tooling.

#mcp#awesome#index
punkpeye
research1.8k

Awesome Claude AI

General-purpose Claude awesome list with a strong security/agent sub-section.

#awesome#claude#index
yzfly
tool30k

Claude Code

Anthropic's official terminal-native agent. Reads/edits code, runs shell, drives MCP servers — the canonical Claude offensive/defensive workhorse.

#cli#claude#official
Anthropic
tool11k

Claude Engineer

Interactive CLI that lets Claude self-improve its own toolset — autonomous file ops, code analysis and security audit loops.

#cli#claude#agent
Doriandarko
tool12k

smol developer

Tiny Claude-driven dev agent — scaffolds whole codebases from a prompt. Adapted for PoC exploit and CTF tooling generation.

#cli#agent#scaffolding
smol-ai
tool13k

Plandex

Terminal AI agent for complex multi-file changes with diff-based review. Useful for large security refactors and code-base hardening.

#cli#agent#multi-model
plandex-ai
tool18k

Goose (Block)

Block's open-source on-machine agent — Claude/GPT/local, MCP-native. Pluggable extensions for shell, edit, computer-use.

#cli#agent#mcp
Block
tool60k

Open Interpreter

Lets LLMs run code (shell, Python, JS, AppleScript) locally with full host access — Claude-compatible. Bread-and-butter for ad-hoc offensive automation.

#cli#agent#shell
Open Interpreter
tool11k

ShellGPT

Command-line productivity tool powered by Claude/GPT — generates shell one-liners for recon, log triage, IR forensics.

#cli#shell#productivity
TheR1D
tool15k

Claudia

GUI + agent runtime for Claude Code with project sandboxing, MCP management and replayable security audit sessions.

#claude-code#gui#agent
Asterisk
tool12k

Crush (Charm)

Charm's terminal AI coding agent — beautiful TUI, MCP-native, multi-provider (Claude, GPT, Gemini, local). Great for SSH-only ops.

#cli#tui#agent
Charm
tool9k

Qwen Code

Alibaba's open-source CLI agent forked from Gemini CLI, tuned for Qwen3-Coder. Useful uncensored alternative for offensive workflows.

#cli#agent#open-weights
Alibaba Qwen
tool

Kimi CLI

Moonshot Kimi K2 1T-param terminal agent — long-context code audit and exploit drafting with a generous free tier.

#cli#agent#long-context
Moonshot AI
tool21k

DeepSeek Coder CLI

Self-hostable DeepSeek-V3 terminal coding agent. Strong code reasoning, weak refusal guardrails — favored for red-team PoCs.

#cli#open-weights#code
DeepSeek
tool17k

Roo Code

Fork of Cline with multi-mode personas (architect, ask, code, debug). Swap between exploit dev and defensive review mid-session.

#vscode#agent#multi-model
Roo Code Inc
tool27k

Continue.dev

Open-source IDE autopilot — Claude / GPT / local. Custom slash-commands make it a great Burp/Semgrep companion for code audits.

#ide#agent#code-audit
Continue
tool9k

llm (Simon Willison)

Swiss-army CLI for any LLM (Claude, GPT, local). Plugin ecosystem includes prompt-injection probes and log triage helpers.

#cli#scripting#plugins
Simon Willison
tool4.6k

mods (Charm)

AI on the command line — pipe nmap/ffuf/gobuster output straight into Claude for inline triage and report drafts.

#cli#pipe#shell
Charm
tool8k

AIChat

All-in-one terminal LLM client (Claude, GPT, Gemini, local). REPL, shell-assist, RAG, function calling — single Go binary.

#cli#multi-model#repl
sigoden
tool1.4k

Agentic Radar

Open-source security scanner for AI agent workflows — maps tools, models, MCP servers and surfaces prompt-injection / data-exfil risk.

#agent-security#scanner#mcp
SplxAI
tool1.2k

MCP-Scan (Invariant Labs)

Security scanner for MCP servers and clients — detects tool poisoning, rug-pulls, cross-server shadowing and prompt-injection sinks.

#mcp#scanner#agent-security
Invariant Labs
tool1.1k

promptmap

Automated prompt-injection vulnerability scanner for Claude/GPT-powered LLM apps — fuzzes system prompts to find leakage paths.

#prompt-injection#scanner#red-team
Utku Sen
research400

AgentDojo

Benchmark for evaluating tool-use agent security against prompt injection — Claude/GPT/Gemini comparative attack success rates.

#benchmark#agent-security#prompt-injection
ETH SPY Lab
tool1.4k

Rebuff

Self-hardening prompt-injection detector — combines heuristic, LLM-based and vector-DB canary detection for Claude apps.

#defense#prompt-injection#detection
Protect AI
tool1.9k

LLM Guard

Comprehensive input/output scanner for LLM apps — PII redaction, prompt-injection blocking, toxicity, jailbreak heuristics.

#defense#guardrails#filter
Protect AI
tool1.7k

ModelScan

Static scanner for ML model files (pickle, h5, savedmodel) — detects code-exec backdoors in HuggingFace artifacts before you load them.

#supply-chain#ml-security#scanner
Protect AI
tool850

Counterfit (Microsoft)

Microsoft's CLI for adversarial ML attacks — evasion, extraction, inversion. Useful when chaining Claude with classifier-based defenses.

#adversarial-ml#cli#red-team
Microsoft / Azure
tool400

Vigil LLM

Detects prompt injections, jailbreaks and untrusted inputs — scanners for Claude/GPT-powered chatbots, RAG and agents.

#defense#prompt-injection#rag
deadbits
mcp1.6k

MCP-for-Security

Curated MCP servers wrapping security tooling (sqlmap, ffuf, masscan, nuclei, amass) — plug-and-play offensive stack for Claude.

#mcp#offsec#pentest
cyproxio
research700

Damn Vulnerable MCP

Intentionally vulnerable MCP server — practice attacking tool-poisoning, indirect prompt injection and confused-deputy bugs in Claude agents.

#mcp#lab#vulnerable
harishsg993010
mcp900

Awesome MCP Security

Dedicated awesome list for MCP security — attacks, defenses, scanners, sandboxing patterns, real-world CVEs.

#mcp#awesome#security
Puliczek
research1.3k

Awesome AI Security

DeepSpace's master AI/LLM security index — defensive tooling, offensive frameworks, papers, courses, datasets, vendors.

#awesome#ai-security#index
DeepSpaceHarbor
research600

Awesome LLM Red Teaming

Living list of LLM red-team techniques, public jailbreaks, payload corpora and tooling — Claude/GPT/Gemini coverage.

#awesome#red-team#jailbreak
user1342
research

Embrace The Red (Johann Rehberger)

Canonical research blog on Claude / ChatGPT / Copilot agent attacks — indirect prompt injection, data exfil, ASCII smuggling, ZombAIs.

#research#agent-security#blog
Johann Rehberger
research

Simon Willison — Prompt Injection

The canonical body of work on prompt injection, exfiltration via markdown images, and LLM-app threat modeling.

#prompt-injection#blog#research
Simon Willison
mcp

CyberSec-MCP Tools

All-in-one cybersecurity MCP server (whois, dig, traceroute, shodan, virustotal, exploitdb, cve search) — one config for Claude.

#mcp#osint#blue-team
giuliosmall
mcp

BloodHound MCP

Exposes BloodHound AD attack paths to Claude — natural-language Active Directory privilege-escalation pathfinding.

#mcp#ad#red-team
MorDavid
mcp

Volatility MCP

Memory-forensics MCP — Claude drives Volatility3 plugins against memory dumps for IR investigations.

#mcp#dfir#forensics
dvlpjrs
mcp

SQLMap MCP

Wraps sqlmap so Claude can autonomously fingerprint, enumerate and dump SQLi targets with safe-rate guards.

#mcp#sqli#web
grec0
mcp

OWASP ZAP MCP

Drives OWASP ZAP active/passive scans from Claude — site enum, alert triage, custom auth scripts.

#mcp#zap#web
Sebbyx
mcp

YARA MCP

Run YARA rules over samples/memory and let Claude write and refine detection rules from threat reports.

#mcp#yara#malware
dasdata