Explore
MCP servers and skills: search, filter by where they run, and compare.
MCP servers and skills: search, filter by where they run, and compare.
817 structured cybersecurity skills for AI agents · Mapped to 6 frameworks: MITRE ATT&CK, NIST CSF 2.0, MITRE ATLAS, D3FEND, NIST AI RMF & MITRE F3 (Fight Fraud) · agentskills.io standard · Works with
SkillApache-2.0★ 35kNo key
The system of action for AI-native cybersecurity—where intent becomes governed execution, evidence becomes operational memory, and every operation improves the next.
GoApache-2.0★ 8.0kNo key
A vendor-neutral collection of Sigma, YARA, and Suricata rules for detecting compromise of LLM applications, MCP servers, ML supply chains, AI infrastructure, AI-powered insider threats, and RAG/vecto
SkillApache-2.0★ 129No key
Zero-Dependency Network Forensics & PCAP Protocol Dissection Engine for AI Agents
Node.jsApache-2.0★ 3Few starsNo key
Red teaming framework that proves whether an MCP-speaking agent can be hijacked by a malicious server
PythonApache-2.0★ 2Few starsNo key
SkillApache-2.0★ 1Few starsNo key
Remote MCP server for Korean stock analysis — real DART filings, KRX quotes, conservative valuation ranges for Claude, Cursor and any MCP client
SkillApache-2.0★ 24No key
Remote automated research skills in engineering
SkillApache-2.0★ 3Few starsNo key
SkillApache-2.0★ 3Few starsNo key
An open agent-skills library for malware analysis, reverse engineering, and threat hunting - 118 curated, runnable skills mapped to MITRE ATT&CK, D3FEND, and CAR.
SkillApache-2.0★ 22No key
PythonApache-2.0★ 1Few starsNo key
The world's first 100% client-side AI watermark stripper. Pure Rust → WASM. Browser extension + web playground. Defeats SynthID, C2PA, and Unicode marks
SkillApache-2.0★ 9No key
Autonomous red-team cockpit: live recon-to-report engagements, with per-command human approval.
SkillApache-2.0★ 2Few starsNo key
Turn goals, existing Skills, and authorized work records into bounded Agent Loops, then export a Codex Skill or Compact Prompt with separate verifiable evidence.
SkillApache-2.0★ 5No key
Local, single-user AI-assisted security testing workflow engine: visual DAG orchestration, deterministic execution, evidence-proof findings. 本地单用户的 AI 辅助安全测试工作流引擎。
PythonApache-2.0★ 3Few starsNo key
Harness, axioms CLI and Cloudflare Workers app template for agent-built apps
SkillApache-2.0★ 2Few starsNo key
AI-assisted host provenance and incident-response workspace
GoApache-2.0★ 5No key
Sovereign Zero-Latency AI Agent & MCP Gateway Daemon with Hermes Paperclip Governance, E2E Testing Framework, and Alibaba Open Code Review
PythonApache-2.0★ 1Few starsNo key
Jam with Claude — an MCP server that turns a described beat into a loopclub link. A pure encoder: holds no keys, signs nothing.
Node.jsApache-2.0Few starsNo key
An image is not a sentence: a VLM's description of one is unvalidated prose. VSON makes every claim about an image — object, property, spatial relation, action — a graph assertion SHACL can reject, so
SkillApache-2.0★ 2Few starsNo key
SkillApache-2.0★ 1Few starsNo key
Zero-Data fine-tuning operations MCP server - 64 tools for the full LLM fine-tuning delivery lifecycle, callable by Claude Code
PythonApache-2.0Few starsNo key
Who stands behind it