cost_guard_models

List all supported models with their per-token pricing.

Server Agent Safety luciferforge/agent-safety-mcp
Category Read
Risk class Low
Parameters 00 required

What cost_guard_models does on Agent Safety

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

Why cost_guard_models needs a policy

This tool retrieves configuration/reference data (supported models and pricing information) without modifying state, executing operations, or committing financial transactions. It is purely informational, making it a Read-category tool.

From the tool's definition Tool name 'cost_guard_models' and description 'List all supported models with their per-token pricing' indicate a retrieval operation that queries and returns static reference data about available models and their costs.

Questions about cost_guard_models

What does the cost_guard_models tool do? +

List all supported models with their per-token pricing. It is categorised as a Read tool in the Agent Safety MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on cost_guard_models? +

Register the Agent Safety MCP server in PolicyLayer and add a rule for cost_guard_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 Agent Safety. Nothing to install.

What risk level is cost_guard_models? +

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

Can I rate-limit cost_guard_models? +

Yes. Add a rate_limit block to the cost_guard_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 cost_guard_models completely? +

Set action: deny in the PolicyLayer policy for cost_guard_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 cost_guard_models? +

cost_guard_models is provided by the Agent Safety MCP server (luciferforge/agent-safety-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.