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 onl...
AI agents call check_qr 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.
This is a read-only verification tool that retrieves and analyzes data against threat intelligence databases. It decodes QR codes and checks URLs against security databases, but does not create, modify, delete, or execute any operations. The scanning and analysis of data with no side effects places it squarely in the Read category.
From the tool's definition The tool 'check_qr' analyzes and decodes QR code images and runs verification checks against threat intelligence databases.
Attacks that exploit this kind of access
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. 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_qr: 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_qr 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_qr 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_qr. 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_qr 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 →