create_thought · Tpc MCP: Risk & Policy

WHAT IT DOES

What create_thought does on Tpc

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

WHY IT NEEDS A POLICY

Why create_thought needs a policy

Creating a thought is a write operation that generates new data. It is reversible (thoughts can typically be deleted or edited) and has no inherent destructive, financial, or code execution implications. The blast radius is minimal since it only adds information to what appears to be a planning or note-taking system.

From the tool's definition Tool name 'create_thought' and description 'Create a new thought' indicate the tool creates new data (a thought entry) in the system.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

create_thought Rate-limited

create_thought 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": {
    "create_thought": {
      "limits": [
        {
          "counter": "create_thought_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 Tpc, so you can run agents against it safely.

FAQ

Questions about create_thought

What does the create_thought tool do? +

Create a new thought. It is categorised as a Write tool in the Tpc MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on create_thought? +

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

What risk level is create_thought? +

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

Can I rate-limit create_thought? +

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

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

create_thought is provided by the Tpc MCP server (suttonwilliamd/tpc-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.