predict_initial_states · Cellrank MCP: Risk & Policy

WHAT IT DOES

What predict_initial_states does on Cellrank

AI agents invoke predict_initial_states to trigger actions in Cellrank. 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 predict_initial_states needs a policy

This tool performs a computational operation (computing/predicting initial states) that triggers external processing of genomic data. It doesn't merely read existing data but actively computes derived results using statistical distributions, making it an Execute category tool.

From the tool's definition Compute initial states from macrostates using coarse_stationary_distribution

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

predict_initial_states Rate-limited

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

FAQ

Questions about predict_initial_states

What does the predict_initial_states tool do? +

Compute initial states from macrostates using coarse_stationary_distribution. It is categorised as a Execute tool in the Cellrank MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on predict_initial_states? +

Register the Cellrank MCP server in PolicyLayer and add a rule for predict_initial_states: 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 predict_initial_states? +

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

Can I rate-limit predict_initial_states? +

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

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

predict_initial_states 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.