F
licenseNot graded
qualityB
maintenancePassive website security and trust auditor that checks for security, SEO, AI surface, email, and other exposures, producing a score and remediation plan.
-
Continuous agent-speed defense for public surfaces
Server Details
Agent-speed defense for your own public surfaces: daily diff probes, per-identity verdicts.
Ownership verified
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-03-26
- URL
- ChatGPT
- –
- Claude
- –
TDQS
C2.5/5.0
Scored across 3 tools
Disambiguation3/5
defense_run and exposure_verdict both produce verdicts on verified surfaces, distinguished only by 'full deterministic probe' vs 'scoped diff verdict' — a subtle boundary an agent could easily confuse. defense_verdicts is clearly a list operation and stands apart.
Naming Consistency2/5
Names mix prefixes (defense_ vs exposure_) and grammatical patterns: defense_run (noun+verb), defense_verdicts (noun+noun), exposure_verdict (noun+noun). There is a loose noun_verb/noun_noun feel but no predictable verb_noun convention.
Tool Count3/5
Three tools is borderline thin for a defense/probe service; a full-probe run, a list, and a scoped verdict leave the surface feeling sparse for the apparent scope.
Completeness2/5
There is no tool to verify, register, or configure a surface (only assumed 'verified surfaces'), no single-verdict retrieval, and no deletion or lifecycle management for stored verdicts — significant gaps likely to cause agent dead ends.
Available Tools
3 toolsdefense_runCInspect
Full deterministic probe of one of your verified surfaces (subscription).
Inputs: surface_id (required).
defense_verdictsCInspect
List your stored verdicts.
Inputs: no named parameters.
exposure_verdictCInspect
Scoped diff verdict for one of your verified surfaces (trial or subscription; the $25 one-off rail is the HTTP /verdict endpoint).
Inputs: surface_id (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Agent rental platform: web-vuln scanning, OSINT and red-team tools via subscription.
Passive OSINT and security recon: DNS, TLS, email posture, IP reputation, CVE/KEV, CT logs.
Audit active CISA KEV ransomware CVEs, SSL/TLS CT log subdomains, SPF/DMARC security & ICANN RDAP.
Discover exposed assets, leaked secrets, APIs & client-side vulns across your attack surface
Related MCP Servers
- AlicenseNot gradedqualityBmaintenanceEnables agents to map a domain's public technology and identity footprint — email providers and controls, identity indicators, SaaS, and cloud infrastructure — as evidence-backed, machine-readable observations marked passive by default, where missing evidence reads as "not observed" rather than "not used". Runs locally with one-domain lookups, multi-domain comparisons, and explicit collection failures.728 PyPI5Apache 2.0
- AlicenseAqualityCmaintenanceProvides anonymous, privacy-preserving tools for AI agents, including prompt-injection scanning, site file validation, endpoint liveness checks, attestation, and risk-pattern analysis.341MIT
- AlicenseNot gradedqualityBmaintenanceEnables AI agents to perform authorized web-pentest reconnaissance and interaction, including crawling, headless-browser control, login/BOLA comparisons, safe probes, HAR replay, and evidence-first reporting, while enforcing declared scope, audit trails, rate limits, and data minimization.1MIT
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd
Glama MCP Gateway
Add one secure layer between your agents and this server.