Agentic cybersecurity tool: URL phishing/malware scanning and more.
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.
Return this account's monthly usage and remaining plan allowance. Args: year: Four-digit UTC year; defaults to the current year. month: UTC month from 1 to 12; defaults to the current month.
This tool isn't marked read-only, so it may change something on the server or in an account you connected.
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
Run in a terminal
claude mcp add --transport http SmartyPantsAPI https://smarty-pants.io/mcp
Return this account's monthly usage and remaining plan allowance. Args: year: Four-digit UTC year; defaults to the current year. month: UTC month from 1 to 12; defaults to the current month.
| Argument | Type | Description |
|---|---|---|
| year | any | |
| month | any |
{
"type": "object",
"title": "get_usageArguments",
"properties": {
"year": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"title": "Year",
"default": null
},
"month": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"title": "Month",
"default": null
}
}
}Scan a single URL for phishing or malware risk. Args: url: The URL to scan. temperature: Optional decision threshold from 0.0 to 1.0. Higher is stricter; when omitted the service default is used.
| Argument | Type | Description |
|---|---|---|
| url* | string | |
| temperature | any |
{
"type": "object",
"title": "scan_urlArguments",
"required": [
"url"
],
"properties": {
"url": {
"type": "string",
"title": "Url"
},
"temperature": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"title": "Temperature",
"default": null
}
}
}Scan several URLs in one request. Args: urls: The URLs to scan. temperature: Optional decision threshold from 0.0 to 1.0. Higher is stricter; when omitted the service default is used.
| Argument | Type | Description |
|---|---|---|
| urls* | array | |
| temperature | any |
{
"type": "object",
"title": "scan_urlsArguments",
"required": [
"urls"
],
"properties": {
"urls": {
"type": "array",
"items": {
"type": "string"
},
"title": "Urls"
},
"temperature": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"title": "Temperature",
"default": null
}
}
}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.
No readOnlyHint / destructiveHint annotations, so clients can't tell a read from a write without asking.
Fix: Add annotations to each tool, e.g. { readOnlyHint: true } for tools that only read.