Search

AI Guardian Firewall — a local, user-space, agent-agnostic firewall that mediates an autonomous AI agent's actions (files, shell, network, services) with a deterministic policy boundary, a tamper-evident audit log, and a human-in-the-loop approval cockpit. No kernel modules. Apache-2.0.

Local-first MCP reverse proxy that blocks sensitive, destructive, or policy-violating tool calls before execution using deterministic rules, DLP matchers, and AST-based intent analysis.

One scored audit of everything you ship: code, sites, apps, APIs, containers, IaC, cloud and mobile. CLI, CI and MCP for AI agents.

Open-source behavioral sandbox for Model Context Protocol (MCP) servers

Sniff and decode BLE GATT traffic, fingerprint device profiles, and assert on insecure pairing/characteristics in CI against a capture.

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

Non-custodial burner wallet for AI agents: make a wallet, check balance, send, swap.

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

[](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.

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

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

UTA Trust Gateway — MCP middleware for enforcing trust decisions on agent tool calls

Runtime call-chain anomaly monitor for MCP servers — rug-pull detection + behavioural anomaly rules, delivered as a CLI, a GitHub Action, and an MCP server.

Nemesis Shield — Sentinel SDK for Python (web/API/LLM behavioral protection). Learn your app's normal behavior, then block off-baseline requests in enforce mode. ASGI/WSGI/Django middleware + OpenAI/Anthropic/LangChain LLM guards.

AntiClaude core engine: agent red-team evals, report compare, local guard, and runtime policy

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

Open-source AST aware code scanner to find your app’s vulnerabilities.

[](https://glama.ai/mcp/servers/suhui-organization/pod) 📇 🏠 🍎 🐧 - Least-privilege compiler for AI agents. Run your agent in record-only mode, compile the smallest policy it actually needs from its real tool calls, enforce it at an MCP gateway (deny > approve > allow), and keep a SHA-256 hash-chained audit that verifies offline. `curl -fsSL https://raw.githubusercontent.com/suhui-organiza

Fracta — auditor de segurança + LGPD multi-agente e determinístico para SaaS (DAST + SAST, relatório A–F). CLI: fracta scan.

Trust & human sign-off for AI agents: approval required before irreversible agent actions