Security & Testing MCP Servers for DeepSeek Harness

Classify AI systems by EU AI Act risk tier, estimate fines, write Art. 50 notices, list deadlines.

Read-only MCP: free OpenAI security evidence ledger (55 fields) + SaaSDossier release register.

Free payment guide and Base-USDC x402 MCP security, package, domain, and SEC tools.

Audits TLS/SSL handshake latency, HSTS headers, and HTTPS availability on the edge.

Audit GitHub Actions workflows for script injection, unpinned actions and missing permissions.

Scan a website's HTTP security headers (HSTS, CSP, framing, COOP/CORP, cookies). Score + fixes.

HMAC-SHA1 hex length, input discarded

HSTS max-age band, value discarded

A secret store for AI agents: the agent never sees the plaintext.

Zero-secret MCP gateway for AI agents: risk-scored, audited calls with human-in-the-loop approval.

Read-only MCP server for Inforcer M365 baseline governance, plus assessment and report runs.

Check an IP or your own network exit before using ChatGPT, Claude, Gemini or Meta Muse.

Is this name on Japan's MOF asset-freeze list? Hosted, list-change history kept. Reference only.

check-package: block malicious npm/PyPI deps before your AI agent installs them. Free, no key.

k-anonymity 5-hex prefix, value discarded

Qualified eIDAS RFC 3161 timestamping for AI workflow provenance. SIGNIUS/IDnow backbone.

Is a CVE exploited? CISA KEV, FIRST EPSS, CVSS and SSVC with a patch-first verdict. Free, no key.

CVE patch-priority API + MCP: CISA KEV, EPSS, CVSS, SSVC. Keys $19/mo; 200 free calls/day.

Compliance & security scan for your app: secrets, exposed files, headers, privacy, AI-disclosure.

Scan URLs or HTML for WCAG 2.2 violations. 75-rule manifest, weighted score, shareable reports.

Cryptographically anchored evidence for agents: verified run receipts, proof-gated settlement.