subsample · Cloudcompare MCP: Risk & Policy

WHAT IT DOES

What subsample does on Cloudcompare

AI agents use subsample to create or update resources in Cloudcompare — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Cloudcompare environment.

WHY IT NEEDS A POLICY

Why subsample needs a policy

Subsampling produces a new, reduced-density point cloud as output. It modifies/transforms data but does not irreversibly delete the original source, making it a Write-level operation. Misuse has limited blast radius as it only affects point cloud density in a derived output.

From the tool's definition 'Reduce the density of a point cloud using random, spatial, or octree subsampling' — creates a new downsampled version of the point cloud

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

subsample Rate-limited

subsample stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "subsample": {
      "limits": [
        {
          "counter": "subsample_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

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

FAQ

Questions about subsample

What does the subsample tool do? +

Reduce the density of a point cloud using random, spatial, or octree subsampling. It is categorised as a Write tool in the Cloudcompare MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on subsample? +

Register the Cloudcompare MCP server in PolicyLayer and add a rule for subsample: 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 Cloudcompare. Nothing to install.

What risk level is subsample? +

subsample is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit subsample? +

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

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

subsample is provided by the Cloudcompare MCP server (yufeioptimal/cloudcompare-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.