"Eight" matching MCP servers:

Publishes four flat, schema-light tools that let AI agents (including strict providers) search, describe, and invoke any of 139 reverse-engineering capabilities behind a persistent REA server. Enables file fingerprinting, inspection, and evidence-linked investigation of shipped software through plain-English requests, read-only by default.

This MCP server lets an agent run local binary inspection on ELF, Mach-O, PE, APK, IPA, ASAR, WebAssembly, and firmware targets — pulling symbols, sections, classified strings, disassembly, and mitigation posture, and flagging dangerous imports and CWE patterns. It exposes eight stdio JSON-RPC tools (with no external API keys) that feed a multi-agent swarm for attack-surface mapping and exploit-chain synthesis.

Serves as an intentionally vulnerable training target that exposes eight planted MCP vulnerability challenges—tool poisoning, rug pulls, path traversal, SSRF, command injection, missing auth, prompt-injection chains, and secrets exposure—each with a patched counterpart so users can exploit, detect, and remediate real-world MCP security flaws.

Enables an AI agent to audit an untrusted repository through eight parameterless MCP tools that run ten pinned security scanners inside a hardened container, returning native scanner reports, a run manifest tied to the scanned tree, and an audit log. The agent gets no shell, no target path, and no way to build or execute the audited code, so hostile repositories cannot steer the analysis.