AI agents call list-gpu-types to retrieve information from RunPod MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The verb 'list' combined with 'gpu-types' indicates this tool retrieves or queries information about available GPU types. There are no side effects, data modifications, deletions, or financial operations implied. Even though the description is empty, the naming convention strongly suggests a read-only information retrieval operation typical of infrastructure inventory queries.
From the tool's definition Tool name 'list-gpu-types' indicates a query/list operation with no descriptive text provided. The '-list' prefix and context within RunPod's API (which manages infrastructure) suggest retrieval of available GPU types without modification.
Documented attack patterns abuse exactly the kind of access list-gpu-types gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and RunPod MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for list-gpu-types:
{
"version": "1",
"default": "deny",
"tools": {
"list-gpu-types": {}
}
}list-gpu-types is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
list-gpu-types. It is categorised as a Read tool in the RunPod MCP Server MCP Server, which means it retrieves data without modifying state.
Register the RunPod MCP Server MCP server in PolicyLayer and add a rule for list-gpu-types: 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 RunPod MCP Server. Nothing to install.
list-gpu-types 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 list-gpu-types 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 list-gpu-types. 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.
list-gpu-types is provided by the RunPod MCP Server MCP server (runpod/runpod-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 36 RunPod MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
36 RunPod MCP Server tools catalogued and risk-classified — across an index of 42,500+ MCP servers.