Policy-as-code gate for MCP. A fail-closed proxy that denies risky tool calls before they run, produces offline-verifiable evidence bundles of what executed, and enforces IPv4/TCP egress in-kernel via eBPF/LSM and Landlock on Linux. Deterministic and offline-first.
Build from source (Rust)
git clone https://github.com/Rul1an/assay.git
cd assay
cargo build --releaseTransparent heuristic — same formula for every entry. Total 60/100.
MCP server for IDA Pro, allowing you to perform binary analysis with AI assistants. This plugin implement decompilation, disassembly and allows you to generate malware analysis reports automatically.
vet-mcp checks open source packages—like those suggested by AI coding tools—for vulnerabilities and malicious code. It supports npm and PyPI, and runs locally via Docker or as a standalone binary for fast, automated vetting.
JADX-AI-MCP is a plugin and MCP Server for the JADX decompiler that integrates directly with Model Context Protocol (MCP) to provide live reverse engineering support with LLMs like Claude.
Beelzebub is a honeypot framework that lets you build honeypot tools using MCP. Its purpose is to detect prompt injection or malicious agent behavior. The underlying idea is to provide the agent with tools it would never use in its normal work.
Exposes the RSigma Sigma detection-engineering toolkit to AI agents over stdio or Streamable HTTP with `rsigma mcp serve`. Tools to author, lint, validate, and convert Sigma detection rules, evaluate and explain detections against log events, and inspect correlation state, all backed by a native Rust engine.
Human sign-off + trust receipts for AI agents: requires a named human's approval before an irreversible action (payment release, record change, deploy), then mints an offline-verifiable Ed25519 Trust Receipt. Also exposes trust profiles, receipt verification, disputes, and delegation. Apache-2.0; policy engine formally verified. Install: `npx -y @emilia-protocol/mcp-server`.