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.
AI agents call check_phone 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_phone is a query/retrieval tool that analyzes input against existing intelligence records and returns risk assessments. It has no side effects, cannot modify data, execute code, delete records, or move money. The blast radius of misuse is minimal—an attacker could profile phone numbers for reconnaissance, but this is a low-severity read operation typical of threat intelligence platforms.
From the tool's definition Tool performs lookups and queries against threat intelligence databases (FTC, FCC, carrier data, community reports) with no indication of modifying data, executing commands, or triggering external actions.
Attacks that exploit this kind of access
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. 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_phone: 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_phone 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_phone 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_phone. 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_phone 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 →