"An incomplete or malformed search query" matching MCP connectors:

Read-only breach intel, full history 2007-today: reports THAT an org was breached, never the data.

~Alter is the identity layer agents query before they transact, answering who is actually on the other end. 11 of the 42 tools work with no account and no key. Call them now and see what comes back. Two calls plus a small proof of work gives your agent its own ~handle. Reads settle in USDC over x402 and 75% goes to the person read. Being known.

Classify data safety before storing or sharing. GDPR, HIPAA, PCI-DSS, CCPA. AI-powered.

Neutral fairness computation for agents: two or more parties submit sealed inputs, a published deterministic algorithm runs (fair division, verifiable random selection, Shapley shares), and every party receives an identical signed certificate anyone can re-run and verify for free.

Scan public websites for privacy, cookie, tracker, consent, policy, and disclosure risk signals. Start instantly with zero-auth Light mode—no account or API key required.

Pay-per-call safety checks for AI agents: screen a crypto address or URL before you transact.

Read-only MCP server for turva.dev, an agent-readiness audit and advisory service.

The PropelAuth Integration MCP Server helps you and your favorite AI agent integrate PropelAuth as quickly and easily as possible into your project. Whether you're integrating PropelAuth into your Next.js project or your FastAPI backend, the Integration MCP Server will ensure your AI agent has the best context possible for a successful integration.

Query OSV.dev for package vulnerabilities and batch-audit dependency lists via MCP.

Verify x402 payment endpoints before an AI agent pays: scam scan, on-chain checks, trust scores.

Ten machine-readable signals on one public page: the top miss if any, and a receipt we re-verify.

Search newly registered, expired, aged, active, deleted and for-sale domains, plus WHOIS and DNS.

Email OS for agents - real-inbox search, triage, commitments, and a verifiable BEC hard-stop.

Query WHOIS/RDAP information for domains, IP addresses, CIDR prefixes and ASNs. Self-hostable.

Free lockfile malware check plus paid pre-install scan of any skill, tool, or package.

Capture a web source, or seal a hash you hold, into a signed receipt anyone can verify offline.

Query 90 days of honeypot probe data: IP reputation, scanners, CVE probing, TLS/SSH fingerprints.

Stop your agent before it runs rm -rf /etc or emails your .env. Deterministic preflight checks.

Query Microsoft Patch Tuesday security updates (MSRC) with EPSS and CISA KEV enrichment

Adversarial verification for AI agents - pay an independent skeptic per verdict in USDC via x402.