store_thought · Rawthink MCP: Risk & Policy

WHAT IT DOES

What store_thought does on Rawthink

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

WHY IT NEEDS A POLICY

Why store_thought needs a policy

Based on the server context (persistent memory, knowledge graph, session lifecycle) and the tool name 'store_thought', this tool likely writes a thought or observation into persistent memory storage. The sibling tools include 'add_observations' and 'create_entities', reinforcing a Write classification.

From the tool's definition Tool name 'store_thought' suggests writing/persisting data; description is empty and uninformative.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

store_thought Rate-limited

store_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": {
    "store_thought": {
      "limits": [
        {
          "counter": "store_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 Rawthink, so you can run agents against it safely.

FAQ

Questions about store_thought

What does the store_thought tool do? +

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

How do I enforce a policy on store_thought? +

Register the Rawthink MCP server in PolicyLayer and add a rule for store_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 Rawthink. Nothing to install.

What risk level is store_thought? +

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

Can I rate-limit store_thought? +

Yes. Add a rate_limit block to the store_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 store_thought completely? +

Set action: deny in the PolicyLayer policy for store_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 store_thought? +

store_thought is provided by the Rawthink MCP server (ygtalp/rawthink-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.