get_fastest
AI agents call get_fastest 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.
This tool retrieves pre-computed latency rankings to help select a model—a read-only query operation with no side effects. The empty description lowers confidence slightly, but context from the server's purpose strongly indicates this queries and returns ranking data rather than modifying state or executing code. Severity is low because incorrect usage (requesting fastest model info) causes no damage.
From the tool's definition Tool name 'get_fastest' on a server that 'ranks [models] by latency' and 'helps AI agents pick the fastest available model' indicates retrieval of ranked performance data. No parameters provided suggesting modification or execution.
Attacks that exploit this kind of access
get_fastest. 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 get_fastest: 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.
get_fastest 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 get_fastest 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 get_fastest. 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.
get_fastest 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 →