MCP Catalog

AI-powered static and contextual code analysis MCP server

Cost-optimized LLM pipeline + 6 AI security skills (reasoning, triage, remediation, compliance).

City hiring-compliance MCP server with regulation search and full audit risk scoring.

PQC scanner for GitHub repos and smart contracts. Detects quantum-vulnerable ECDSA/RSA.

GeraWitness MCP (placeholder) — human-in-the-loop safety layer for AI agents. Launching 2026.

EU AI Act and GDPR compliance: checks, audits, generate policies.

Privacy protection: scans, tracker detection, data broker opt-outs.

Ricardian contracts for AI agents — dual-format, SHA-256 bound, legible by construction.

Cloudflare Turnstile CAPTCHA solver for AI agents. $0.002/call, 100 free on signup. P95 2.2s.

Command your AI agents: verifiable passports, credential injection, full audit, revoke in 60s.

On-chain trust verification and Street Cred for AI agents. ERC-8004, multi-chain.

Minimal MCP server for Ghost Security API - compatible with all MCP clients

Agent reputation scoring: trust scores, Sybil detection, cross-chain identity for 133K+ agents

Departure and admission records for AI agents with Ed25519/P-256 signatures.

Multi-model code review: a panel of models + detectors return a pass/fail verdict. Paid via x402.

Free browser-based calculators and analyzers for cloud cost, DevOps, security, and data governance.

MCP server for Incode IDV, providing identity verification tools for AI assistants.

Security audit for AI agents — scan code/diffs for leaked secrets, check deps via OSV.

SSRF-safe URL fetch for AI agents — clean markdown/text/HTML/JSON, plus guarded REST calls.

Hardened filesystem for AI agents — jailed root, read-only default, traversal/symlink-safe.

AML/CFT compliance oracle: wallet screening, sanctions, PEPs, jurisdiction risk.

Forensic FX audit. Detects hidden bank markups in real time. Returns spread bps + audit score 1-10.

Sanctions, PEP, KYB, and competitive intelligence on any company. Panama Papers cross-check.

Stop a rogue AI agent and prove what it tried: signed receipts, tool policies, output verification.