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.
AI agents call check_text to retrieve information from ScamVerify without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
check_text retrieves threat intelligence data and performs static analysis on provided text content, generating risk assessments as output. This is a pure Read operation—it queries databases and applies analysis logic without creating, modifying, executing code, deleting data, or initiating financial transactions.
From the tool's definition Tool performs analysis and cross-referencing of text messages against threat intelligence databases (10M+ records from FTC, FCC, URLhaus, ThreatFox).
Attacks that exploit this kind of access
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. It is categorised as a Read tool in the ScamVerify MCP Server, which means it retrieves data without modifying state.
Register the ScamVerify MCP server in PolicyLayer and add a rule for check_text: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches ScamVerify. Nothing to install.
check_text is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the check_text rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for check_text. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
check_text is provided by the ScamVerify MCP server (scamverifyai/scamverify-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →