Retrieve all streaming output from a Serverless job by polling until the job reaches a terminal state. The worker must support streaming output. Polls /stream/{jobId} repeatedly and collects every chunk until status is COMPLETED, FAILED, CANCELLED, or TIMED_OUT.
AI agents call stream-job 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 retrieves job output data and polls an endpoint to collect results. It performs no write, execute, destructive, or financial operations. However, it is classified as 'medium' severity rather than 'low' because: (1) it retrieves potentially sensitive output/logs from serverless jobs that may contain proprietary code, credentials, or private data; (2) an agent with this capability could exfiltrate job…
From the tool's definition Tool description states it 'Retrieve[s] all streaming output' and 'Polls /stream/{jobId} repeatedly and collects every chunk until status is COMPLETED, FAILED, CANCELLED, or TIMED_OUT'.
Risk signalsBulk/mass operation — affects multiple targets
Documented attack patterns abuse exactly the kind of access stream-job 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 stream-job:
{
"version": "1",
"default": "deny",
"tools": {
"stream-job": {}
}
}stream-job 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.
Retrieve all streaming output from a Serverless job by polling until the job reaches a terminal state. The worker must support streaming output. Polls /stream/{jobId} repeatedly and collects every chunk until status is COMPLETED, FAILED, CANCELLED, or 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 stream-job: 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.
stream-job 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 stream-job 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 stream-job. 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.
stream-job 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.