High Risk →

pause_consumption

Pause consumption of a realtime table

How to control pause_consumption ↓

What pause_consumption does on StarTree MCP Server for Apache Pinot

AI agents invoke pause_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.

High Risk

Why pause_consumption needs a policy

This tool triggers an external operation that halts data ingestion for a realtime table in Apache Pinot. It is not merely reading data, nor does it permanently delete anything, but it actively changes the operational state of a running system. Misuse could cause data loss or significant lag in a production streaming pipeline, making the blast radius high.

From the tool's definition Pause consumption of a realtime table

Documented attack patterns abuse exactly the kind of access pause_consumption gives an agent:

How to control pause_consumption

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 pause_consumption:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "pause_consumption": {
      "limits": [
        {
          "counter": "pause_consumption_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

pause_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.

  1. Create a free account and register StarTree MCP Server for Apache Pinot — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
RATE-LIMIT THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about pause_consumption

What does the pause_consumption tool do? +

Pause 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.

How do I enforce a policy on pause_consumption? +

Register the StarTree MCP Server for Apache Pinot MCP server in PolicyLayer and add a rule for pause_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.

What risk level is pause_consumption? +

pause_consumption is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit pause_consumption? +

Yes. Add a rate_limit block to the pause_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.

How do I block pause_consumption completely? +

Set action: deny in the PolicyLayer policy for pause_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.

What MCP server provides pause_consumption? +

pause_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.

Enforce policy on every StarTree MCP Server for Apache Pinot tool call.

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.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.