Returns raw pricing and capability data for LLM models matching the supplied filters.
AI agents call get_pricing 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.
The tool queries and retrieves publicly available or pre-cached pricing information about LLM models. It has no side effects, does not execute code, does not modify data, and does not commit financial obligations. Misuse by an agent (e.g., repeated calls) would be a low-severity information disclosure or DoS risk, not a security or financial threat.
From the tool's definition Tool returns pricing and capability data; no modifications, deletions, or financial transactions. Description states 'Returns raw pricing and capability data' — a read-only retrieval operation.
Attacks that exploit this kind of access
Returns raw pricing and capability data for LLM models matching the supplied filters. 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 get_pricing: 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.
get_pricing 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_pricing 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_pricing. 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_pricing 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 →