run_clustering · ProduckAI MCP Server MCP: Risk & Policy

WHAT IT DOES

What run_clustering does on ProduckAI MCP Server

AI agents invoke run_clustering to trigger actions in ProduckAI MCP Server. 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.

WHY IT NEEDS A POLICY

Why run_clustering needs a policy

This tool executes a data analysis pipeline (clustering algorithm) that processes feedback data and generates insights. While the operation itself is not destructive or financial, it runs external computational logic whose behavior and outputs depend on the input data. This fits the Execute category as it triggers external operations.

From the tool's definition Tool description states it will 'Trigger the clustering pipeline' and 'Run this after uploading new feedback' - uses explicit verb 'Trigger' and 'Run' indicating execution of an automated process.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

run_clustering Rate-limited

run_clustering 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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "run_clustering": {
      "limits": [
        {
          "counter": "run_clustering_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches ProduckAI MCP Server, so you can run agents against it safely.

FAQ

Questions about run_clustering

What does the run_clustering tool do? +

Trigger the clustering pipeline to analyze feedback and generate themes and insights. Clustering groups similar feedback together using AI to identify patterns and create actionable insights. Run this after uploading new feedback or when you want to refresh the analysis. It is categorised as a Execute tool in the ProduckAI MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on run_clustering? +

Register the ProduckAI MCP Server MCP server in PolicyLayer and add a rule for run_clustering: 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 ProduckAI MCP Server. Nothing to install.

What risk level is run_clustering? +

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

Can I rate-limit run_clustering? +

Yes. Add a rate_limit block to the run_clustering 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 run_clustering completely? +

Set action: deny in the PolicyLayer policy for run_clustering. 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 run_clustering? +

run_clustering is provided by the ProduckAI MCP Server MCP server (rohitsaraff33-bit/produckai-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.