Resume consumption of a realtime table
AI agents invoke resume_consumption to trigger actions in StarTree MCP Server for Apache Pinot. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool triggers an external operational state change on a realtime table — resuming data consumption. It is not merely reading or writing data records, but executing a control-plane action that changes the operational state of a streaming pipeline. Misuse could cause unintended data ingestion, resource consumption spikes, or disrupt carefully managed pause states, making it high severity.
From the tool's definition Resume consumption of a realtime table
Documented attack patterns abuse exactly the kind of access resume_consumption gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and StarTree MCP Server for Apache Pinot, and nothing reaches the server without passing your rules. This is the rule we recommend for resume_consumption:
{
"version": "1",
"default": "deny",
"tools": {
"resume_consumption": {
"limits": [
{
"counter": "resume_consumption_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
} resume_consumption stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Resume consumption of a realtime table. It is categorised as a Execute tool in the StarTree MCP Server for Apache Pinot MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the StarTree MCP Server for Apache Pinot MCP server in PolicyLayer and add a rule for resume_consumption: 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 StarTree MCP Server for Apache Pinot. Nothing to install.
resume_consumption is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the resume_consumption 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 resume_consumption. 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.
resume_consumption is provided by the StarTree MCP Server for Apache Pinot MCP server (startreedata/mcp-pinot). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from StarTree MCP Server for Apache Pinot, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
26 StarTree MCP Server for Apache Pinot tools catalogued and risk-classified — across an index of 43,000+ MCP servers.