check_text
Read-onlyIdempotent
Analyze text messages for scam indicators by extracting phone numbers and URLs, then cross-referencing them with threat intelligence to identify scam types, red flags, and calculate risk scores.
Instructions
Analyze a text/SMS message for scam indicators. Extracts and cross-references embedded phone numbers and URLs. AI analysis identifies scam type, red flags, and risk level. Returns unified risk score combining AI and sub-lookup signals.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| message | Yes | Text message content to analyze (max 5000 characters) | |
| from_number | No | Sender phone number, if known |
Implementation Reference
- src/index.ts:196-221 (handler)Implementation of the 'check_text' MCP tool, which analyzes text messages for scam indicators using an API call.
// 3. check_text server.tool( 'check_text', 'Analyze a text/SMS message for scam indicators. Extracts and cross-references embedded phone numbers and URLs. AI analysis identifies scam type, red flags, and risk level. Returns unified risk score combining AI and sub-lookup signals.', { message: z.string().describe('Text message content to analyze (max 5000 characters)'), from_number: z.string().optional().describe('Sender phone number, if known'), }, { title: 'Analyze Text Message', readOnlyHint: true, destructiveHint: false, idempotentHint: true, openWorldHint: true, }, async ({ message, from_number }) => { try { const body: Record<string, unknown> = { message }; if (from_number) body.from_number = from_number; const data = await apiPost('/api/v1/text/analyze', body); return jsonResult(data); } catch (err) { return errorResult(err instanceof Error ? err.message : 'Text analysis failed'); } }, );