PhishDestroy CTI
Server Details
Read-only phishing-domain intelligence: check domains, dated evidence reports, search by brand.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 7 tools
fetch and get_domain_report both retrieve a single domain's report, differing only in argument shape (detail/sections/cursor vs. plain id), which is a classic misselection trap. get_cti_stats vs get_platform_stats also have adjacent meanings ('CTI aggregates' vs. 'report-database counters'), and search vs lookup_domains overlap on domain lookup, though batch size and brand/prefix matching do help separate those two.
All names are snake_case and readable, but the verb conventions are mixed: bare verbs (fetch, search), get_* (three tools), lookup_*, and probe_*. The pattern is not predictable enough to guess a tool name from intent, and 'fetch' is notably vague next to 'get_domain_report'.
Seven tools is well within a reasonable scope for a read-only threat-intel server. The only drag is that fetch and get_domain_report look like two entry points for one operation, so the effective surface is closer to six.
The core read path is covered: search/batch-lookup for discovery, report retrieval for evidence, live probe for liveness, and two stats endpoints for aggregates. There is no bulk export or enumeration-by-brand listing endpoint, and takedown is only reported as a link/status rather than an operation, but these are minor gaps for a CTI read surface.
Available Tools
7 toolsfetchRead a reportARead-onlyIdempotentInspect
Read one PhishDestroy domain report found with search (id = domain): record status, assessment, third-party verdicts with dates, availability, takedown and evidence links, as text and JSON (phishdestroy.domain-report.v1, detail summary).
Inputs: id (required). Returns: id, url, text, title, +1 more
get_cti_statsGet CTI aggregatesBRead-onlyIdempotentInspect
Return CTI aggregates. Confirmed takedowns and latest-check unavailability are separate fields.
Inputs: no named parameters.
get_domain_reportGet stored domain reportARead-onlyIdempotentInspect
Return the stored evidence record for one domain, including dated detections and report links. With detail (summary, evidence or full), sections, max_chars or cursor it returns the compact phishdestroy.domain-report.v1 structure instead: record status (listed, not_found, removed, withdrawn), the PhishDestroy assessment apart from third-party verdicts, dated availability with conflicts, confirmed takedown, evidence links and paged observations. Without these arguments the original record is returned unchanged.
Inputs: domain (required), cursor, detail, sections, +1 more.
get_platform_statsGet platform statisticsARead-onlyIdempotentInspect
Return current PhishDestroy report-database counters with metric definitions and source timestamps.
Inputs: no named parameters.
lookup_domainsCheck many domainsARead-onlyIdempotentInspect
Check up to 25 domains in one call: record status per domain (listed, not_found, removed, withdrawn) with the report URL, first-recorded time and confirmed takedown. not_found is not a safety verdict. Unicode names, URLs and defanged [.] input are normalised; invalid entries are listed separately. For evidence call get_domain_report with detail summary.
Inputs: domains (required). Returns: format, limits, schema, invalid, +2 more
probe_domainProbe domain livenessARead-onlyIdempotentInspect
Run a rate-limited live HTTP probe for a public domain. The result is liveness evidence, not a safety verdict.
Inputs: domain (required).
searchSearch published reportsARead-onlyIdempotentInspect
Search published PhishDestroy domain reports by a domain (exact; URLs and defanged input accepted), the start of a domain name (3+ characters) or an impersonated brand as stored (e.g. Coinbase, MetaMask). Returns up to 20 results (id = domain, title with the first-recorded date, url = report page), newest brand matches first. Read one with fetch. An empty result is not a safety verdict.
Inputs: query (required). Returns: note, results
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Check domain availability and prices, and look up any domain's public records. Read-only.
Public phishing feed: suspicious/confirmed phishing URLs detected hourly. No auth, CC0.
Domain intelligence for DNS, WHOIS/RDAP, TLS, reputation, valuation, and brand protection.
Read-only honeypot observations and evidence. Invite-only API key; request access on our website.
Related MCP Servers
- AlicenseNot gradedqualityBmaintenanceProvides MCP tools to query the phishunt.io phishing feed, enabling domain checks, brand-specific phishing lists, delta syncs, and phishing-signal analysis.1MIT
- AlicenseAqualityDmaintenanceDomain intelligence for DNS, WHOIS/RDAP, SSL/TLS, subdomain discovery, availability, valuation, email security, and typosquatting and brand protection.12MIT

domaintrackofficial
AlicenseNot gradedqualityBmaintenanceEnables users to look up a domain's stored reputation snapshot, its AI crawler policy from robots.txt, and the catalogue of data sources behind those answers through a keyless public endpoint.67 npmMIT- AlicenseNot gradedqualityDmaintenanceEnables domain intelligence lookups including RDAP registration data, DNS records, and Certificate Transparency searches.1MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.