Search

Authensor MCP Server - Stripe, GitHub, and HTTP tools with policy enforcement

Tool-integrity pinning for MCP. Pin what your agent approved; block it when it changes.

🪐 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.

Temporary package placeholder for staged publishing

Open-source red teaming toolkit for AI agents, RAG systems, MCP servers, and tool-using LLM applications.

Provenance-aware authorisation for LLM agent tool calls, a defence against indirect prompt injection and data exfiltration.

AI Agent 付款安全层: 身份/意图/密钥 三道信任支柱 + 四道闸门。给 AI 定义带消费上限的数字身份, 防提示注入, 密钥不落盘。Python + MCP

Does this MCP endpoint serve its tool list to an unauthenticated caller? A runtime probe that emits a signed receipt of what it observed.

Betterleaks Cloud - GitHub, Git, S3, Dir Secret Scanner

One command to keep secrets out of AI. Works with Claude Code, Cursor, Copilot, Windsurf, and any AI coding tool.

MCP server that points an AI agent at a LIVE URL and confirms which secret files are publicly served — exposed .git, .env, JS source maps, backup/SQL dumps, directory listing and dotfiles — by fetching the bytes, not a checklist. Zero deps, read-only.

MCP firewall for AI Agents. Blocks rug pull attacks, tool poisoning, and prompt injection via schema integrity checks and policy-as-code.

Bawbel — The Open Trust Layer for Autonomous Software Identity. Authority. Behavior. Trust. Policy. Enforcement. Evidence.

Portable, model-agnostic cybersecurity sub-agent exposed via MCP, CLI, and Python API.

Threat modeling, code/cloud/pipeline scanning, shadow-AI discovery, compliance checks and fixes.

A deterministic layer between untrusted content and agent actions: it removes the hidden layer, remembers where data came from, and keeps calls inside the boundaries of the intent.

🐍 🏠 🍎 🪟 🐧 - Deterministic AI safety policy engine with Z3 formal verification. Write, verify, and enforce machine-verifiable constraints for AI agents via MCP.

Node wrapper for the Armorer Guard local Rust scanner and MCP proxy.

[](https://glama.ai/mcp/servers/boy-offi9-inc/hexforge-gateway) 📇 🏠 ☁️ 🐧 - AI-assisted APK reverse-engineering workspace. Orchestrates jadx, apktool, adb, and frida as MCP agents through a Workflow engine, with a stdio MCP Server Frontend for Claude Desktop/Code/Cursor. Runs on Termux (Android) or PC; Supabase persistence is opt-in.

EP-MCP middleware (reference implementation). Wraps an MCP tool-call handler: irreversible tool calls route through consent → Class-A signoff → an emitted EP-RECEIPT-v1 + an appended provenance entry; everything else passes through. Includes the demand ho