generate_thought_experiment · CBT Agent Helper MCP

WHAT IT DOES

What generate_thought_experiment does on CBT Agent Helper

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

WHY IT NEEDS A POLICY

Why generate_thought_experiment needs a policy

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

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

generate_thought_experiment Rate-limited

generate_thought_experiment 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": {
    "generate_thought_experiment": {
      "limits": [
        {
          "counter": "generate_thought_experiment_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 CBT Agent Helper, so you can run agents against it safely.

FAQ

Questions about generate_thought_experiment

What does the generate_thought_experiment tool do? +

generate_thought_experiment. It is categorised as a Write tool in the CBT Agent Helper MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on generate_thought_experiment? +

Register the CBT Agent Helper MCP server in PolicyLayer and add a rule for generate_thought_experiment: 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 CBT Agent Helper. Nothing to install.

What risk level is generate_thought_experiment? +

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

Can I rate-limit generate_thought_experiment? +

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

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

generate_thought_experiment is provided by the CBT Agent Helper MCP server (sundai-club/cbt-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.