Get the health and operational status of a Serverless endpoint, including worker counts and job statistics.
AI agents call endpoint-health 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.
This tool only retrieves existing status data about an endpoint; it does not create, modify, delete, or execute any operations. The 'Get' verb and focus on querying operational metrics align with the Read category. Severity is low because the data returned is non-sensitive operational metadata that does not grant access to customer data or enable misuse with significant blast radius.
From the tool's definition Tool description states 'Get the health and operational status' — a retrieval operation with no modification or execution. It queries endpoint metrics (worker counts, job statistics) similar to status/monitoring endpoints.
Documented attack patterns abuse exactly the kind of access endpoint-health 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 endpoint-health:
{
"version": "1",
"default": "deny",
"tools": {
"endpoint-health": {}
}
}endpoint-health 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.
Get the health and operational status of a Serverless endpoint, including worker counts and job statistics. 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 endpoint-health: 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.
endpoint-health 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 endpoint-health 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 endpoint-health. 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.
endpoint-health 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.