predict_terminal_states · Cellrank MCP: Risk & Policy

WHAT IT DOES

What predict_terminal_states does on Cellrank

AI agents use predict_terminal_states 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 predict_terminal_states needs a policy

An AI agent can call predict_terminal_states faster than any human can review — one bad instruction and it creates or modifies resources in Cellrank by the hundred, each call as confident as the last.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

predict_terminal_states Rate-limited

predict_terminal_states 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": {
    "predict_terminal_states": {
      "limits": [
        {
          "counter": "predict_terminal_states_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 predict_terminal_states

What does the predict_terminal_states tool do? +

Predict terminal states from macrostates. This automatically selects terminal states from the computed macrostates. 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 predict_terminal_states? +

Register the Cellrank MCP server in PolicyLayer and add a rule for predict_terminal_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_terminal_states? +

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

Can I rate-limit predict_terminal_states? +

Yes. Add a rate_limit block to the predict_terminal_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_terminal_states completely? +

Set action: deny in the PolicyLayer policy for predict_terminal_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_terminal_states? +

predict_terminal_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.