private_thinking_delta · Claude Imagine MCP: Risk & Policy

WHAT IT DOES

What private_thinking_delta does on Claude Imagine

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

WHY IT NEEDS A POLICY

Why private_thinking_delta needs a policy

This tool creates or modifies data (the thinking bubble message content) in a reversible manner. It is a write operation that updates display state without executing external code, deleting data, or causing financial impact. The scope is limited to UI message updates within the Claude Imagine interface.

From the tool's definition Tool name 'private_thinking_delta' and description 'Update the thinking bubble message' indicate modification of an existing UI message element within the visual builder.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

private_thinking_delta Rate-limited

private_thinking_delta 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": {
    "private_thinking_delta": {
      "limits": [
        {
          "counter": "private_thinking_delta_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 Claude Imagine, so you can run agents against it safely.

FAQ

Questions about private_thinking_delta

What does the private_thinking_delta tool do? +

Update the thinking bubble message. It is categorised as a Write tool in the Claude Imagine MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on private_thinking_delta? +

Register the Claude Imagine MCP server in PolicyLayer and add a rule for private_thinking_delta: 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 Claude Imagine. Nothing to install.

What risk level is private_thinking_delta? +

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

Can I rate-limit private_thinking_delta? +

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

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

private_thinking_delta is provided by the Claude Imagine MCP server (t3rm1nu55/claudeimagine). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.