Security & Testing MCP Servers for DeepSeek Harness

35-probe LLM/agent security red-team scan (injection, jailbreak, MCP abuse) with report.

LM hash 16-hex shape, value discarded

Send API keys and private files to someone else's agent, end-to-end encrypted.

NIST 800-171 controls and 800-171A objectives, crosswalks, exact SPRS scoring, POA&M generation.

2,029 DISA STIG rules with official check/fix text, CCI mappings, and .ckl checklist export.

MCP server for Mailprotector — customers, domains, users, quarantine, allow/block rules for MSPs.

Submit files and URLs to a malware sandbox, poll scans, fetch reports, hashes and IOCs.

Analyzes threats and verifies URLs align with the agent's intended goal.

Safe, self-hosted ZAP operator for guided AI security scans and reports.

Scan any MCP server for tool-poisoning, security, auth & license. Trust score before install.

Browser QA agent that won't return a false green: verified PASS/FAIL + access-control probing.

Check if a counterparty is safe to pay: trust/risk score for AI agents. Scam/phishing screen.

Check npm packages for typosquats, hallucinated names, install scripts and risky new releases.

Detect malicious or vulnerable npm packages: registry search, OSV.dev and GitHub advisory lookups

Stateful Windows RPC attack-surface research for AI agents: 22 tools on NtObjectManager.

Real-time threat intel for AI agents: 890K+ IOCs incl. prompt-injection & AI-skill threats

Security & DLP proxy for MCP: tool-poisoning scans, PII redaction on tool args/results. Beta.

$0.01/call via x402: OFAC wallet screen, DNS, email auth, domain age, email verify, URL unshorten.

Security incidents across Nigeria, such as kidnapping and banditry, with sources and confidence.

Free no-account URL security scan: 0-100 Launch Readiness score for any live site in ~15 seconds.

Pay-per-call TLS, DNS/email-auth and expiry checks, plus a $2 full site audit (x402 USDC).