"A guide to understanding AI agents" matching MCP connectors:
GET /v1/connectors – MCP directory API referenceMatching Connector Tools:
Agentic cybersecurity tool: URL phishing/malware scanning and more.
Adversarial testing for AI agents that move money: engine battery, Ed25519-sealed verdict reports.
34 security tools for AI agents: phishing links, exposure maps, DNS, SSL, PQC, history, pivots.
The Smarty-Pants MCP provides a ranking of the probability a URL is malicious. Designed as an agentic cybersecurity product. 1000 requests free with developer account (also free but must sign up). Easy to use return JSON: { "url": "http://evil.co/1", "probability": 0.987787, "malicious_percent": 98.78, "is_malicious": true, "threshold": 0.6, "source": "model" }
The main MCP server has 10 tools, including six public, read-only CVE tools, site search and page reading. CVE results include source software/version evidence and available CISA KEV and dated FIRST EPSS data. The separate request_security_test action requires an agent key, consent and authorization. A no-account, read-only CVE-only endpoint is https://excessionlabs.ai/mcp/cve. Docs: https://excessionlabs.ai/cve-intelligence/.
Free website privacy scanner for pre-consent cookies, trackers, consent, policy, and HTTPS/TLS.
Check a package version for known vulnerabilities and Packagist release facts.
Grade a page's HTTP security headers, search penetration testing guides and send a pentest request for a person. The read tools need no authentication; request_pentest needs a free agent key.
30 security tools + the Vigia agent to audit MCP servers before you connect.
Live security incidents, updated hourly from CISA KEV, critical GitHub security advisories, CVE records, vendor advisories and security news. For each one: what's affected, whether a fix exists, which versions fix it, and the sources. Check a lockfile or a whole repo and get the exact upgrade. Lockfiles are read in memory and never stored. Read-only MCP server, no auth
30 security tools + the Vigía agent to audit MCP servers for prompt injection, SSRF, leaked secrets, auth bypass and more — scan before you connect.
Free email checks: 24 blacklists, spoofing grade, redirects, spam test, WHOIS, BIMI, AI readiness.
Free passive outside security scan of a live web app: leaked keys, exposed files, open Supabase
CVSS Calculator MCP is a lightweight MCP server that enables AI agents to accurately calculate CVSS Base Scores and severity ratings. Supports CVSS 2.0, 3.0, 3.1, and 4.0 for vulnerability assessment, penetration testing, bug bounty hunting, and security reporting.
Prompt-injection scanner for agents: risk score, categories and spans for text, pages, MCP tools
Triage a CVE: how severe it is, whether it is exploited, and how likely exploitation is.
Fetches a public http(s) URL (GET, up to 5 redirects, 10s timeout, body never read) and grades its security headers A+ to F: score, present and missing headers (HSTS, CSP, X-Frame-Options, Referrer-Policy, Permissions-Policy), per-header findings with copy-paste fix values, and cookie flag issues. Passive, SSRF-guarded. Pay-per-call via x402 ($0.01 USDC on Base); initialize and tools/list are free.
Scan a site or AI-built app for exposed databases, keys and MCP endpoints, then verify the fixes.
Test your AI agents for security and safety weaknesses, and re-verify the fixes.
Security reviews, threat models over a repo or website, and remediation tracking, in your editor.
Scan a website's HTTP security headers (HSTS, CSP, framing, COOP/CORP, cookies). Score + fixes.
Free AI test helpers: injection inputs, OWASP mapping, release plans, response and tool-call packs.
Production-safety audits for AI-generated code, with a fix for every finding.
Smart-contract security audits for EVM chains and DAML: quote, run and fetch reports.
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).
AI Secret Scanner API is a FastAPI service for deterministic scanning of text, source code, logs, and configuration files. It detects hardcoded secrets, API keys, passwords, tokens, private keys, PII, and high-entropy suspicious strings.
Audits security headers + TLS (HSTS, CSP, cert, cookies) for any site. $1.50/call via x402.
Argues against a security finding or a draft bug bounty report before you submit it.
Tells your coding agent whether your installed packages need patching, with advice on what to do.
Passive security check of a domain: headers, TLS, DNS and email authentication. No login needed.
Uncensored models for authorized security testing, prices readable without a key
Free Slither scan of Solidity contracts for AI coding agents; optional paid report (1 USDC, x402).
Free hosted CVE intel for bug-bounty agents: CVE fact-check, attack approaches from paid H1 reports
Audit a dependency list for known vulnerabilities, licenses and outdated versions.
Security scanner for AI agents: prompt injection, leaked secrets, PII, and SSRF-risk URL detection.
Agents that white-hack your app for a full day and report what attackers could exploit.
Pre-install security scans for npm packages, MCP servers, and AI agents with cited verdict evidence.
Scan PDFs, Office docs, and RAG files for malware exploits, macros, CVEs, and AI prompt injection.
Live post-quantum (PQC) exposure of any domain, with a QEX score and sealed quantum evidence.
Read AI security guides and lab research, and request an LLM or AI agent security assessment.
Review saved CyberLens website and repository scans through read-only OAuth tools.
Supply chain security: free npm lockfile malware check, paid scan of packages, skills, MCP servers.
Prompt-injection Guard checks and public AI red-teaming arena data from Heisto on Solana.
Router default logins, compliance index, MAC/OUI lookup. Reads free; submit_correction is Pro.
Human-reviewed audit of a public website: bugs, passive security checks, UX. Order link for owners.
Security checks for AI-built apps (Lovable, Supabase, Bolt): RLS, headers, monitoring, fixes.
Jailbreak resistance tester for LLM agents: DAN, role-play, encoding bypass probes.
Security scanner for AI agents and MCP servers: injection, jailbreak, tool abuse.
Run real, auto-recovered cloud attacks on AWS, Azure and GCP to test your defenses.
Exploited vulnerabilities, critical CVEs, breaches and AI security incidents, with primary sources.
Audit any live URL: 85 SEO, AI-search, security, leaked-key and speed checks, with fixes to verify.
Prompt injection and system-prompt extraction testing for LLM agents. Free 8-probe sample.
AI agent security audit: red-team probes plus missing-guardrail review with fixes.
Human-reviewed security certificates and ops audits for AI agent skills, paid per job.
Reputation for IPs, domains, URLs, hashes, emails, phones; CVEs; injection and email scans
Free security scan for AI-written GitHub repos: leaked keys, .env, eval, SQLi, CORS.
Free passive security scan for AI-built apps: leaked API keys, public .env files, security headers
Solve reCAPTCHA image grids, text captchas, GeeTest and FunCAPTCHA for AI agents. Free tier.
Gandoki is a precision-first MCP security scanner featuring 55 detectors, layered evidence verification, AI-assisted false-positive suppression, and read-only credential validation. Discover exposed secrets, debug interfaces, and sensitive files across authorized assets with explainable findings and minimal noise.
CVE lookups (NVD) and dependency-manifest audits (OSV) for AI agents. No API keys.