filter_and_normalize · Cellrank MCP: Risk & Policy

WHAT IT DOES

What filter_and_normalize does on Cellrank

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

WHY IT NEEDS A POLICY

Why filter_and_normalize needs a policy

This tool modifies scientific data through filtering (removal) and normalization (transformation). While the effects are technically reversible if the original data is retained separately, within the context of a single analysis session, these transformations alter the working dataset irreversibly.

From the tool's definition Tool description explicitly states it will 'filter and normalize' data, which modifies the AnnData object in-place or creates a modified version.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

filter_and_normalize Rate-limited

filter_and_normalize 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": {
    "filter_and_normalize": {
      "limits": [
        {
          "counter": "filter_and_normalize_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 Cellrank, so you can run agents against it safely.

FAQ

Questions about filter_and_normalize

What does the filter_and_normalize tool do? +

Preprocess data: filter and normalize AnnData object for velocity/pseudotime analysis. It is categorised as a Write tool in the Cellrank MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on filter_and_normalize? +

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

What risk level is filter_and_normalize? +

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

Can I rate-limit filter_and_normalize? +

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

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

filter_and_normalize is provided by the Cellrank MCP server (scmcphub/cellrank-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.