SniffPup
Server Details
Free passive outside security scan of a live web app: leaked keys, exposed files, open Supabase
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- ChatGPT
- –
- Claude
- SniffPup
TDQS
Scored across 1 tool
There is only one tool, so there is no possibility of misselection or overlap. Its purpose (passive site scan returning a score and issues) is unambiguous.
The single name scan_site follows the standard verb_noun snake_case convention and is descriptive. With only one tool there is no broader pattern to evaluate, so it cannot be a full 5.
A single tool is thin for a server that stores scans and tracks a free scan allowance, suggesting additional operations exist conceptually. It is borderline rather than wrong, since the core action is one operation.
The scan itself is well-covered, including evidence, fixes and consent handling. However, the tool stores scans and consumes an allowance yet there is no way to retrieve past scans, check remaining allowance, or delete stored data, leaving clear dead ends.
Publisher details
- Operator
- Ember and Saru LLC
- Operator website
- https://sniffpup.com
- Vendor relationship
- First-party
- Documentation
- https://sniffpup.com/docs/mcp
- Privacy policy
- Not provided
- Trust center
- Unknown
- Restrictions
- Scan only sites you own or are authorized to test. Free MCP/site scans are passive and informational: not a penetration test, audit, certification, or security guarantee. Follow SniffPup Terms of Service.
Available Tools
1 toolscan_siteFree scan of a siteAInspect
Runs SniffPup's free passive scan of a live website (takes up to about a minute) and returns the score and the issues found. Every critical issue comes with masked evidence, fix steps and a fix prompt (with no critical issue, one other issue does). The scan is for a site the user owns or has permission to test. It stores a scan and counts toward the free scan allowance. consent records the user's confirmation: I own this site or can test it, and agree to the Terms, including individual arbitration.
Inputs: url (required), consent (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Free passive security scan for AI-built apps: leaked API keys, public .env files, security headers
Security scans for AI-built apps: leaked keys, open Supabase RLS, vulnerable packages, live sites.
Outside-in audit of a live site: leaked keys, headers, TLS, SPF/DMARC, privacy, SEO, with fixes
Discover exposed assets, leaked secrets, APIs & client-side vulns across your attack surface
Related MCP Servers
- AlicenseAqualityBmaintenanceScan a deployed site for an exposed Supabase service_role key and audit Row Level Security from your AI coding agent.2460 npmMIT
- AlicenseAqualityCmaintenanceSecurity checks for apps built with AI coding tools (Lovable, Bolt, Cursor, Claude Code). Scans a public GitHub repo for open Supabase tables, exposed keys, unprotected server functions and unverified webhooks, and returns each finding with the file and a fix prompt.2419 npmMIT
- AlicenseAqualityBmaintenanceRead-only Supabase Row Level Security review. Analyzes an exported catalog query (no keys needed) for RLS turned off, policies that are just true, anon-callable SECURITY DEFINER functions, views exposing auth.users, public Storage buckets and more, and explains each rule.4MIT
- AlicenseAqualityCmaintenanceEnables AI agents to perform passive security scans on domains, checking email spoofing (DMARC/SPF/DKIM), TLS weaknesses, security headers, exposed files, and subdomain-takeover risk without needing an API key.769 npmMIT
Glama MCP Gateway
Add one secure layer between your agents and this server.