
Read-only phishing-domain intelligence: check domains, dated evidence reports, search by brand.
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh it.
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).
The id of a search result (a domain).
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
Run in a terminal
claude mcp add --transport http cti https://phishdestroy.io/api/mcp.php
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).
| Argument | Type | Description |
|---|---|---|
| id* | string | The id of a search result (a domain). |
{
"type": "object",
"required": [
"id"
],
"properties": {
"id": {
"type": "string",
"maxLength": 300,
"minLength": 4,
"description": "The id of a search result (a domain)."
}
},
"additionalProperties": false
}Return CTI aggregates. Confirmed takedowns and latest-check unavailability are separate fields.
No arguments.
{
"type": "object",
"properties": {},
"additionalProperties": false
}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it returns the compact phishdestroy.domain-report.v1 structure instead: record status (listed, not_found, removed, withdrawn), the PhishDestroy assessment apart from third-party verdicts, dated availability with conflicts, confirmed takedown, evidence links and paged observations.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.
| Argument | Type | Description |
|---|---|---|
| cursor | string | observations.next_cursor from a previous answer. |
| detail | string | Compact report depth. summary: status, assessment, verdicts, availability, takedown, links. evidence: adds registration and paged observations. full: adds machine-generated analysis and untrusted page text. |
| domain* | string | Domain name without a path (Unicode names are accepted with the compact arguments). |
| sections | array | Only these sections (record is the status, page_content is untrusted text from the site). |
| max_chars | integer | Upper bound for the JSON size; pages are shortened and optional sections dropped first, with truncated, omitted_sections and continue in the answer. |
{
"type": "object",
"required": [
"domain"
],
"properties": {
"cursor": {
"type": "string",
"maxLength": 200,
"description": "observations.next_cursor from a previous answer."
},
"detail": {
"enum": [
"summary",
"evidence",
"full"
],
"type": "string",
"description": "Compact report depth. summary: status, assessment, verdicts, availability, takedown, links. evidence: adds registration and paged observations. full: adds machine-generated analysis and untrusted page text."
},
"domain": {
"type": "string",
"description": "Domain name without a path (Unicode names are accepted with the compact arguments)."
},
"sections": {
"type": "array",
"items": {
"enum": [
"record",
"assessment",
"third_party",
"signals",
"availability",
"takedown",
"registration",
"observations",
"evidence",
"analysis",
"page_content",
"limits"
],
"type": "string"
},
"minItems": 1,
"description": "Only these sections (record is the status, page_content is untrusted text from the site).",
"uniqueItems": true
},
"max_chars": {
"type": "integer",
"maximum": 200000,
"minimum": 1000,
"description": "Upper bound for the JSON size; pages are shortened and optional sections dropped first, with truncated, omitted_sections and continue in the answer."
}
},
"additionalProperties": false
}Return current PhishDestroy report-database counters with metric definitions and source timestamps.
No arguments.
{
"type": "object",
"properties": {},
"additionalProperties": false
}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.
| Argument | Type | Description |
|---|---|---|
| domains* | array | Domain names (URLs are accepted; only the host is used). |
{
"type": "object",
"required": [
"domains"
],
"properties": {
"domains": {
"type": "array",
"items": {
"type": "string",
"maxLength": 300
},
"maxItems": 25,
"minItems": 1,
"description": "Domain names (URLs are accepted; only the host is used)."
}
},
"additionalProperties": false
}Run a rate-limited live HTTP probe for a public domain. The result is liveness evidence, not a safety verdict.
| Argument | Type | Description |
|---|---|---|
| domain* | string | Public domain name without a path. |
{
"type": "object",
"required": [
"domain"
],
"properties": {
"domain": {
"type": "string",
"description": "Public domain name without a path."
}
},
"additionalProperties": false
}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.
| Argument | Type | Description |
|---|---|---|
| query* | string | Domain, start of a domain name, or brand name. |
{
"type": "object",
"required": [
"query"
],
"properties": {
"query": {
"type": "string",
"maxLength": 253,
"minLength": 2,
"description": "Domain, start of a domain name, or brand name."
}
},
"additionalProperties": false
}We read every tool's name, description and inputs the way the model will, looking for instructions hidden from you. A clean result means no warning signs, not a guarantee. Scanned Nov 17, 2026.