Security Scanning

Comprehensive Wireshark + Nmap MCP server for network analysis with threat intelligence

Scan MCP servers and agent tool manifests for poisoning, exfiltration, secrets and supply-chain risk

Deterministic, no-LLM security scanner for MCP servers, plus an inline proxy gate.

HMAC-signed zero-width invisible canary token generator and output response leak auditor

Checks declared npm/PyPI dependencies against real registries to catch slopsquatting

Scans ML model files (PyTorch, safetensors, Keras, ONNX) for supply-chain risks

Scans agent code for untrusted input poisoning persistent cross-session memory

Finds PII and credentials in PDFs, screenshots and scanned documents

Read, write and scan process memory, Cheat Engine style, on Windows, Linux and macOS.

Dependency vulnerability scanner with EPSS scoring. 9 MCP tools. Free tier + x402.

WAF security testing: 5,500+ payloads, 25 WAF fingerprints, 21 recon checks, bypass AI

Open-source AI context firewall for governed model, retrieval, memory, and tool access.

Approved acceptance criteria served over MCP to Claude Code, Cursor, or Codex. Git-only, sealed.

Routes each task to the few skills, MCP servers and tools that fit it.

Wraps the ShimGuard CLI as a single generic MCP tool for agent-shim provenance checks.

Provenance gateway for stdio MCP servers: blocks tool calls fed by untrusted tool results.

Scan local or remote hosts for open TCP ports. Runs locally.

Authorization layer between AI agents and money: ALLOW/APPROVAL/DENY, budgets, audit.

AI agent security: prompt injection detection, semantic memory, output scanning, prompt hardening

Policy-based governance for AI agent tool calls. YAML policy, approval gates, audit logging.