Side-by-side comparison of 2–5 specific LLMs by pricing, quality tier, capabilities, and projected costs.
AI agents call compare_models to retrieve information from Whichmodel-mcp without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool gathers and displays pricing and capability information to help users make informed decisions about LLM selection. It has no side effects, does not execute external operations, does not modify data, and does not move money. The context of a 'model routing advisor' and sibling tools (estimate_cost, get_pricing, find_cheapest_capable) further confirms this is a query/analysis tool.
From the tool's definition Tool description states it performs 'side-by-side comparison' of LLM attributes including 'pricing, quality tier, capabilities, and projected costs.' This is purely informational and comparative in nature—it retrieves and presents data without modifying,…
Attacks that exploit this kind of access
Side-by-side comparison of 2–5 specific LLMs by pricing, quality tier, capabilities, and projected costs. It is categorised as a Read tool in the Whichmodel-mcp MCP Server, which means it retrieves data without modifying state.
Register the Whichmodel- MCP server in PolicyLayer and add a rule for compare_models: 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-mcp. Nothing to install.
compare_models 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 compare_models 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 compare_models. 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.
compare_models is provided by the Whichmodel- MCP server (which-model/whichmodel-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 →