"A Minecraft server with a personal API key" matching MCP connectors:

Production-safety audits for AI-generated code, with a fix for every finding.

Patronus SecurityAOAuth

studio.patronus

Scan text, documents, websites, and MCP metadata for prompt injection and sensitive-data risks.

Hosted, no-auth endpoint of feldspar-scan: free deterministic security scan of a public git repository (OSV.dev vulnerable dependencies, secret patterns, config lint) as structured JSON. Tools: scan_repository(url), audit_pricing(). Stateless streamable-HTTP JSON-RPC, rate-limited. Source: https://github.com/project-feldspar-resources/feldspar-scan (MIT). Operated by Feldspar, an autonomous AI agent (Project Feldspar).

Passive domain-perimeter checks — cert expiry, subdomain takeover, lookalikes — as agent tools

Penetration Testing Cost: the site's own MCP server — enquiry (enquiry = a human handoff, not a...

ContrastAPIA

com.contrastcyber

55 tools, 7 Resources, Sigma rules, email SPF/DMARC, MITRE, CVE/KEV, risk_score. No key.

Read-only agent-commerce audit, upgrade verification, diagnosis and x402 probing.

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

WHOIS/RDAP, DNS, SSL, live subdomains with IPs, and SPF/DMARC/DKIM for any domain.

Scan what a public site or AI-built app exposes. Returns a signed, exploitability-graded claim.

Search and audit NIST NVD CVEs by keyword, severity, CWE, CISA KEV status, and CPE.

MCP server: static security scanner for MCP servers, agent skills & plugins. 17 attack patterns.

CVE lookups (NVD) and dependency-manifest audits (OSV) for AI agents. No API keys.

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

Offline methodology engine for authorized penetration testing, CTF, and security research.

Scan, monitor and fix a live web app from your editor: graded security reports with fix prompts.

Check a live app you own for public databases, leaked keys and exposed files.

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

Explain a regex in plain English and detect catastrophic backtracking risk.

Scan a page for hidden prompt-injection payloads targeting AI agents.