List available GPUs across all providers with pricing
AI agents call infra_list_gpus to retrieve information from ML Lab MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves GPU availability and pricing data without making any changes to infrastructure, executing code, or committing financial resources. It is purely informational, making it a Read classification with low severity since the blast radius of misuse is minimal—an AI agent could only retrieve information it is designed to access.
From the tool's definition Tool name 'infra_list_gpus' and description 'List available GPUs across all providers with pricing' indicate retrieval of information only. The verb 'list' is explicitly a Read operation with no modification, deletion, or execution of external systems.
Attacks that exploit this kind of access
List available GPUs across all providers with pricing. It is categorised as a Read tool in the ML Lab MCP MCP Server, which means it retrieves data without modifying state.
Register the ML Lab MCP server in PolicyLayer and add a rule for infra_list_gpus: 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 ML Lab MCP. Nothing to install.
infra_list_gpus 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 infra_list_gpus 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 infra_list_gpus. 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.
infra_list_gpus is provided by the ML Lab MCP server (pushpullcommitpush/ml-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 →