Security Review

Automated red-team checks for trading backtests: lookahead lint, Deflated Sharpe, costs. Local.

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

Deterministic repository change-impact analysis for engineers and coding agents.

Static code map generator: MAP.md + map.json for any repo, plus a Claude Code /map plugin

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

Scans code, IaC and AI-agent config for security problems. Read-only — nothing can be edited.

Twelve tools to inspect CRAP scores, find work, and check edited functions against their ceiling.

Which Python library APIs changed after your model's training cutoff (static diff, no model calls)

Source-linked CodeGraph exploration, ranked search, and static navigation for coding agents.

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

Local-first, read-only MCP server for evidence-backed repository memory.

Deterministic repo architecture maps: auth coverage, blast radius, readiness score, diagrams

Search CVE vulnerability records from the NIST NVD database. No key required.

Find the LLM/AI calls you didn't need — where plain code or a regex does the job. No model.

Security scanner for MCP servers and skill files. Detects AVE vulnerabilities before production.

Evidence-backed Android repository knowledge for humans and AI agents

Keyless Model Context Protocol server for live, verifiable real-world data. Every datapoint is returned in a provenance envelope (source, licence, exact measurement timestamp, age) and Ed25519-signed; records can be independently time-stamped by an independent RFC 3161 authority for proof-of-existe…

Evidence-first security review of authorized repositories. Read-only, root-confined, no shell.

Compiler-precise code property graph for C, Python, and TypeScript, navigable over MCP.