MCP servers and skills: search, filter by where they run, and compare.
Security scanner for MCP server configurations. 10/10 OWASP MCP Top 10 coverage. Auto-fix, tool poisoning detection, rug pull alerts.
PythonMIT★ 2Few starsNo key
AI agent safety layer for crypto transactions - blocks honeypots, blacklists, and rug pulls before they happen
PythonMIT★ 9No key
Runtime behavioral security for Agentic Skills — deterministic policy engine, human-in-the-loop gate, full OWASP Agentic Skills Top 10 (AST01–AST10) coverage. Not another SKILL.md scanner: traces what
PythonMIT★ 1Few starsNo key
MCP server for Marcus Rug Intel — 19 tools for crypto token risk analysis, rug pull detection, and AI forensics. Works with Claude Desktop, Cursor, Windsurf.
PythonMIT★ 1Few starsNo key
Local-first, CI-native security scanner for MCP servers — OWASP MCP Top 10 rules, lockfile & AIBOM. Never executes your servers.
PythonApache-2.0Few starsNo key
Security scanner for MCP servers: tool poisoning, rug pulls, auth bypass, schema hygiene — zero dependencies, passive and safe
PythonMITFew starsNo key
Offline, zero-dependency risk scanner for MCP (Model Context Protocol) client configs — grades each configured server A-F for supply-chain and secret-exposure risk. No network calls, ever.
PythonMITFew starsNo key
Runtime call-chain anomaly monitor for MCP servers — rug-pull detection + behavioural anomaly rules, as a CLI, GitHub Action, and MCP server.
PythonMITFew starsNo key
Zero-trust, risk-aware gateway proxy for the Model Context Protocol (MCP) — enforces identity-scoped tool access, detects schema drift ("rug pull") attacks, scores tool-call risk, and produces a tampe
PythonMIT★ 3Few starsNo key
CI-first conformance testing and benchmarking CLI for MCP servers. Lint your MCP server before your users do.
PythonMITFew starsNo key
Security auditor for locally installed MCP servers - config hygiene + tool-definition rug-pull detection
PythonMITFew starsNo key
SkillRay — AI Skill Security Scanner. Lightweight, offline, multi-engine static analyzer for AI agent skills. 5 engines (Regex + AST + Entropy + Dataflow + Prompt), 37+ rules across 9 threat categorie
SkillApache-2.0★ 2Few starsNo key
Local-first security middleware for MCP servers. Content scanning, prompt-injection defence, trust boundaries, manifest integrity, and audit trails. No API keys, no telemetry. OWASP MCP Top 10 aligned
PythonMITFew starsNo key
MCP Armor continuously secures and monitors Model Context Protocol operations through static and dynamic scans, revealing hidden risks in agent-to-tool communications.
PythonApache-2.0★ 124No key
MCP server exposing Bawbel Scanner as agent-callable tools. Scan MCP servers, skill files, and system prompts for AVE vulnerabilities mid-conversation.
PythonApache-2.0★ 2Few starsNo key
A continuous, out-of-band trust and reliability layer for the Model Context Protocol. Detects tool-definition drift, rug pulls and capability widening across MCP servers.
PythonApache-2.0Few starsNo key
Open-source security scanner for MCP servers — catches hidden Unicode payloads, rug-pulls, and hardcoded secrets
PythonMIT★ 2Few starsNo key
Runtime security scanner for MCP tool poisoning. Native Claude Code plugin.
PythonMIT★ 3Few starsNo key
Who stands behind it
