A dockerized Pentest-Suite capable of running AI-Powered full security checks .
Minimal example of an OAuth 2.1 Authorization Server (FastAPI) and a separate Resource Server (FastMCP) aligned with MCP protocol revision 2025‑06‑18
Library containing OAuth Dynamic Client Registration (DCR) functionality for MCP servers
Rack/Roda-compatible resource-server toolkit for Oauth2.1 MCP Auth
MCP server that bridges AI agents to OpenVAS / Greenbone Vulnerability Management.
Ghidra MCP server that extracts decompiled binary context and exposes it to LLMs via Model Context Protocol.
Burp MCP Mobile Integration is a Flutter-based application that allows you to control a specialized fork of Burp MCP Server configurations and real-time request permissions from a mobile interface. Bo
Home-lab Ghidra: drive one Ghidra Server from your GUI and AI agents over MCP, working the same repositories.
Enterprise reference architecture for governed Agentic SOC, MSSP, MDR, Cloud IR, and private/local LLM-assisted DFIR operations.
MCP servers for Android pentesting with Claude: ADB, Apktool, JADX, Frida, Objection, Burp
CLI and MCP server for Okta SSO authentication with persistent session management
MCP server for PhishTank and Google Safe Browsing — check and verify phishing and malware URLs.
Turn your Convex Auth app into an OAuth 2.1 Provider — perfect for MCP servers
MCP Vault — Gestion sécurisée des secrets pour agents IA (OpenBao embedded). 39 outils MCP, SSH CA, policies, audit, 14 types de secrets style 1Password.
Audit all locally configured MCP servers for permission risks, prompt injection threats, and schema drift
Universal OAuth middleware library for MCP (Model Context Protocol) servers with support for any OAuth provider.
Burp Suite MCP bridge for traffic triage, replay, bounded interception, rewrite automation, and evidence export.
An Model Context Protocol (MCP) server for Fleet. Query OSQuery data, check compliance, and investigate CVEs natively from Claude, Cursor, and any MCP-compatible AI agent.
Plateforme française open source de cybersensibilisation pour PME. AGPLv3 · souverain FR · phishing simulé · vishing IA · NIS2 · RGPD · self-host gratuit ou cloud à partir de 0 €.
Governed MCP server for IP cameras (VAPIX + ONVIF SOAP): fail-closed per-agent policy, hash-chained signed receipts on every call — including denials. First reference producer for the AAR spec.
Experimental Python Trust Kernel for agent interoperability, authorization, budgets, durable governance and verifiable evidence. Bounded protocol support; production qualification pending.
A minimal MCP-HTTP-template that allows to distribute MCP server access via API-key authorization instead of the more complex OAuth approach.
One MCP stdio endpoint for a whole toolchain — GitHub, GitLab, cloud, mail, browser and research tools — with capability-gated dispatch, a machine-checked ABI, and cartridges fetched on demand from bo
Local-first MCP credential broker: agents use gated APIs through scoped, audited requests without ever seeing the secret.
Operator attribution and digital evidence tools specialized for the digital advertising ecosystem—aggregating websites linked to suspicious connections into operator clusters and generating reproducib
Mask secrets in a project with stable placeholders, encrypt the originals, and restore them byte-for-byte. Guards Claude Code, Codex, Gemini CLI, Cursor and Copilot, and blocks git commits that leak s
A simple IDA Pro MCP Server for your reverse engineering needs.
Comprehensive Model Context Protocol (MCP) server for BurpSuite Pro security testing integration with Claude Desktop
MCP server for syncable cli which scans code repo for security risks, vulnerabilities and project overview.
Secure fleet management for Raspberry Pi clusters. Backups, patching, and Docker control with zero plaintext secrets.
AetherScope V2 — SAST 3D WebGL & Serveur MCP (Claude/Antigravity/Cursor). Détection de 150+ CWE & Zero-Day Patterns (Rust, C++, PHP, Node.js, Web3), contrats EARS BLAKE3 et PoC Bug Bounty.
EU AI Act runtime deny for AI agents. Python SDK, TrustLint, MCP.
Security, schema and token-cost checks for MCP servers and AI agent tools. Static analysis that never runs your code, with policy gates for CI, SARIF, and a deliberate 'n/a' when a scan could not read
Evals & guardrails for AI agents and the MCP tools they call: lint + auto-fix, fuzz, SHIP/FIX-FIRST/BLOCK verdict, live guard. Runs in CI, Claude Code, Codex, Cursor.
MCP Server for Ghidra Last Updates
Zero Trust for Agentic AI. Secure Every Tool Boundary. Control which AI agents can use which tools
Directorio completo
IAM, análisis y secretos. 1,343 servidores, los más usados primero. Cada uno abre la página del publicador.