ScamVerify
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| SCAMVERIFY_API_KEY | No | API key for ScamVerify API. Get a free key at https://scamverify.ai (Settings > API Keys). Prefix: sv_live_ for production, sv_test_ for testing. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
| prompts | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| check_phoneA | Look up a US phone number to check for scam reports, carrier info, network status, robocall flags, and community reports. Returns a risk score (0-100), verdict, and detailed signals from FTC, FCC, carrier, and community data. |
| check_urlA | Check a website URL for safety. Analyzes domain age, SSL certificate, redirect chains, brand impersonation, Google Web Risk, URLhaus, ThreatFox, and community reports. Returns risk score and detailed signals. |
| check_textA | 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. |
| check_emailA | Analyze an email for phishing indicators. Checks sender domain, email headers (SPF/DKIM/DMARC), brand impersonation, embedded URLs and phone numbers. Returns unified risk score with detailed header and sender analysis. |
| check_documentA | Analyze a document image for scam indicators. Upload a photo of a suspicious letter, court notice, receipt, invoice, or other document. Uses vision AI to extract entities (addresses, officials, citations, phone numbers) and verifies them against government databases. Returns risk score, verdict, red flags, and entity verification results. |
| check_qrA | Analyze a QR code image. Decodes the QR code server-side and, if it contains a URL, runs full URL verification (domain age, SSL, brand impersonation, URLhaus, ThreatFox, Google Web Risk). Useful for verifying QR codes on parking meters, restaurant menus, mail, and packages. Consumes URL quota only when a URL is found. |
| batch_phoneA | Look up multiple phone numbers in a single request (max 100). Each number is checked individually with the same analysis as check_phone. Returns results array with per-item risk scores and a summary. |
| batch_urlA | Check multiple URLs in a single request (max 100). Each URL is analyzed individually with the same checks as check_url. Returns results array with per-item risk scores and a summary. |
| get_usageA | Check your current API usage quota and rate limits for the billing period. Shows per-channel usage (phone, URL, text, email, document) with limits and remaining counts. QR lookups consume URL quota. |
| get_statusA | Check the operational status of ScamVerify API services. Returns health status for each component (phone, URL, text, email, document lookups, database, AI inference). No authentication required. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| investigate_phone | Investigate a suspicious phone number for scam indicators and provide a safety recommendation. |
| verify_url | Check if a website URL is safe to visit and provide a detailed safety assessment. |
| analyze_text | Analyze a suspicious text message for scam indicators and explain the findings. |
| check_email | Analyze a suspicious email for phishing indicators and provide a safety assessment. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 10 tools
Each tool has a distinct, non-overlapping purpose based on input type (phone, URL, email, text, document, QR) and operation mode (single vs. batch). The 'check_' prefix clearly identifies analysis tools, while 'batch_' and 'get_' group utility functions, leaving no ambiguity about which tool to invoke for a given scam verification task.
All 10 tools follow a consistent snake_case verb_noun convention (check_phone, batch_url, get_status). The verb choices are semantically coherent: 'check' for analysis operations, 'batch' for bulk processing, and 'get' for administrative retrieval, creating a predictable naming scheme throughout the set.
With 10 tools, the server hits the sweet spot for a scam verification API. The set includes single-item checks for six input types, batch variants for high-volume channels (phone/URL), and essential administrative tools (status/usage), with no redundant or filler tools.
The surface covers all major scam vectors (voice, web, email, SMS, physical documents, QR codes) with appropriate AI and database verification. Minor gap: batch operations are only available for phone and URL lookups, not for email, text, or document analysis, though this may reflect typical usage patterns.