Check the status of an asynchronous Serverless job. Returns the current status and output when complete. Job statuses: IN_QUEUE, IN_PROGRESS, COMPLETED, FAILED, CANCELLED, TIMED_OUT.
AI agents call get-job-status 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 purely retrieves information about an existing job's status and results. It has no side effects, does not execute code, does not modify data, and does not delete or move resources. It is a straightforward monitoring/querying operation analogous to checking job status in any task queue system.
From the tool's definition Tool name 'get-job-status' and description 'Check the status of an asynchronous Serverless job. Returns the current status and output when complete.' indicate a read-only query operation that retrieves job state without modifying or triggering any actions.
Documented attack patterns abuse exactly the kind of access get-job-status 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 get-job-status:
{
"version": "1",
"default": "deny",
"tools": {
"get-job-status": {}
}
}get-job-status 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.
Check the status of an asynchronous Serverless job. Returns the current status and output when complete. Job statuses: IN_QUEUE, IN_PROGRESS, COMPLETED, FAILED, CANCELLED, TIMED_OUT. 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 get-job-status: 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.
get-job-status 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 get-job-status 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 get-job-status. 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.
get-job-status 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.