Compare multiple OCI GPU shapes side-by-side on specs, pricing, and price-per-GPU metrics.
AI agents call compare_gpu_shapes to retrieve information from Cloud Cost MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and displays pricing and specification data for OCI GPU shapes side-by-side. It performs no mutations, does not execute workloads, does not delete data, and does not commit financial transactions. It is purely informational comparison, falling clearly into the Read category with minimal risk if misused by an AI agent.
From the tool's definition Tool description states 'Compare...on specs, pricing, and price-per-GPU metrics' - a data retrieval and comparison operation with no modification or execution.
Attacks that exploit this kind of access
Compare multiple OCI GPU shapes side-by-side on specs, pricing, and price-per-GPU metrics. It is categorised as a Read tool in the Cloud Cost MCP MCP Server, which means it retrieves data without modifying state.
Register the Cloud Cost MCP server in PolicyLayer and add a rule for compare_gpu_shapes: 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 Cloud Cost MCP. Nothing to install.
compare_gpu_shapes 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_gpu_shapes 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_gpu_shapes. 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_gpu_shapes is provided by the Cloud Cost MCP server (jasonwilbur/cloud-cost-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 →