scan
AI agents call scan to retrieve information from Model Radar without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The 'scan' tool likely initiates real-time pings or queries of LLM model status across providers—consistent with the server's core function of gathering latency and availability data. This is a read operation (no side effects beyond network queries). The empty description lowers confidence slightly (0.9 rather than 0.95+), but the server's purpose strongly suggests data retrieval.
From the tool's definition Tool named 'scan' on a server that 'pings 130+ free coding LLM models' and 'ranks them by latency'. The server's stated purpose is querying model status and performance data.
Attacks that exploit this kind of access
scan. It is categorised as a Read tool in the Model Radar MCP Server, which means it retrieves data without modifying state.
Register the Model Radar MCP server in PolicyLayer and add a rule for scan: 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 Model Radar. Nothing to install.
scan 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 scan 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 scan. 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.
scan is provided by the Model Radar MCP server (srclight/model-radar). 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 →