batch_remember · Thought MCP: Risk & Policy

WHAT IT DOES

What batch_remember does on ThoughtMCP

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

WHY IT NEEDS A POLICY

Why batch_remember needs a policy

This tool creates and stores data (memories) in a cognitive architecture system. Creating memories is a reversible write operation—memories can be forgotten, edited, or overwritten later via tools like batch_forget or consolidate_memories. It does not execute external code, delete irreversibly, or move financial assets.

From the tool's definition Tool creates memories in batch operation. Description states: 'Create multiple memories in a single batch operation.' The verb 'create' indicates data modification without deletion.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

batch_remember Rate-limited

batch_remember 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": {
    "batch_remember": {
      "limits": [
        {
          "counter": "batch_remember_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 ThoughtMCP, so you can run agents against it safely.

FAQ

Questions about batch_remember

What does the batch_remember tool do? +

Create multiple memories in a single batch operation. It is categorised as a Write tool in the ThoughtMCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on batch_remember? +

Register the Thought MCP server in PolicyLayer and add a rule for batch_remember: 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 ThoughtMCP. Nothing to install.

What risk level is batch_remember? +

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

Can I rate-limit batch_remember? +

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

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

batch_remember is provided by the Thought MCP server (keyurgolani/thoughtmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.