"The most widely used models" matching MCP connectors:
GET /v1/connectors – MCP directory API referenceMatching Connector Tools:
Security reviews, threat models over a repo or website, and remediation tracking, in your editor.
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" }
30 security tools + the Vigia agent to audit MCP servers before you connect.
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/.
Sourced data on 66 penetration testing providers: scope, delivery, published prices, retests. Read-only. Excession Labs publishes it and is one of the rows.
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.
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.
Scan a site or AI-built app for exposed databases, keys and MCP endpoints, then verify the fixes.
Punycode ACE prefix, host discarded
Uncensored models for authorized security testing, prices readable without a key
TE / transfer-encoding token shape
MDN HTTP Observatory — grade any website's HTTP security headers and get the specific fixes, from…
MCP server for the Vulners.com API
Penetration Testing Cost: the site's own MCP server — enquiry (enquiry = a human handoff, not a...
Free front-end security check for any website: a grade plus the secrets and keys it exposes.
Scan the open TCP ports of your own public IP. Fast (32) or deep (65535). No key, no signup.
Find the right security-disclosure contact for any internet asset (domain, IP, package, repo, app).
Test your AI agents for security and safety weaknesses, and re-verify the fixes.
Security scans for AI-built web apps, starting with Lovable. Verify ownership, run authorized scans, inspect findings, get AI-ready fix prompts and request retests. Uses OAuth with a Guarita account. Fix prompt access follows the account plan.
Scan a page for content planted to hijack an AI browsing/shopping agent before it acts on the page.
Look up hosts in the Ohey web malware feed, read CVEs and scan URLs with Ohey's scanner.
Checks a site built with AI tools for security problems and gives the fix in plain English.
Odin connects your coding agent to your organisation’s security findings. Read findings and remediation, inspect pentests and assets, and link an existing fix pull request. Sign in with your Odin account; access follows your organisation role and the permissions you grant. Requires an Odin account.
Programmatic control of the Hiro security platform: scans, tasks, plans, and approvals.
Query and retrieve information about various adversarial tactics and techniques used in cyber atta…