compare_models

Compare costs across multiple models for the same workload. Returns cheapest, best value (quality/price), and best quality options with a recommendation.

Server AgentCost MCP Server oneagentlabs/agentcost-mcp
Category Read
Risk class Low
Parameters 00 required

What compare_models does on AgentCost MCP Server

AI agents call compare_models to retrieve information from AgentCost MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Why compare_models needs a policy

This tool retrieves and queries pricing and model information to enable cost comparison analysis. It has no side effects; it does not create, modify, or delete data, execute code, or trigger financial transactions. The core function is data retrieval and analysis to inform decision-making, which is characteristic of a Read operation.

From the tool's definition Tool 'compare_models' returns cost comparison data and recommendations without modifying any state. The description states it 'Returns cheapest, best value (quality/price), and best quality options' — purely informational retrieval.

Questions about compare_models

What does the compare_models tool do? +

Compare costs across multiple models for the same workload. Returns cheapest, best value (quality/price), and best quality options with a recommendation. It is categorised as a Read tool in the AgentCost MCP Server MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on compare_models? +

Register the AgentCost MCP Server 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 AgentCost MCP Server. Nothing to install.

What risk level is compare_models? +

compare_models is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit compare_models? +

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.

How do I block compare_models completely? +

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.

What MCP server provides compare_models? +

compare_models is provided by the AgentCost MCP Server MCP server (oneagentlabs/agentcost-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

// LOOK UP ANOTHER 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 →

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.