Estimate the cost of a specific workload for a given model.
AI agents call estimate_cost to retrieve information from Whichmodel without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries pricing data and performs cost estimation calculations, which are read operations with no side effects. It provides advisory information to help users make decisions about model selection, but does not commit any financial obligations, execute external operations, or modify any state. The tool is purely informational.
From the tool's definition Tool name 'estimate_cost' and description 'Estimate the cost of a specific workload for a given model' indicate a read-only query that retrieves pricing information and performs a calculation.
Attacks that exploit this kind of access
Estimate the cost of a specific workload for a given model. It is categorised as a Read tool in the Whichmodel MCP Server, which means it retrieves data without modifying state.
Register the Whichmodel MCP server in PolicyLayer and add a rule for estimate_cost: 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 Whichmodel. Nothing to install.
estimate_cost 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 estimate_cost 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 estimate_cost. 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.
estimate_cost is provided by the Whichmodel MCP server (simonamsharp/routewise-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 →