memory_write_episode · Threadwork MCP: Risk & Policy

WHAT IT DOES

What memory_write_episode does on Threadwork

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

WHY IT NEEDS A POLICY

Why memory_write_episode needs a policy

This tool creates or appends new memory records to a persistent SQLite database. While the modification is reversible (memory can be recalled, updated, or cleared via other tools), it irreversibly commits data to long-term storage, making it a Write operation.

From the tool's definition Tool description states it 'Append[s] an episode (long-term memory row)' which indicates creating/adding a new persistent memory record. The deduplication and size capping mechanisms show this modifies stored data.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

memory_write_episode Rate-limited

memory_write_episode 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": {
    "memory_write_episode": {
      "limits": [
        {
          "counter": "memory_write_episode_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 Threadwork, so you can run agents against it safely.

FAQ

Questions about memory_write_episode

What does the memory_write_episode tool do? +

Append an episode (long-term memory row) for a task. Content is hashed and deduped per task; per-task total is capped at 1MB. It is categorised as a Write tool in the Threadwork MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on memory_write_episode? +

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

What risk level is memory_write_episode? +

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

Can I rate-limit memory_write_episode? +

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

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

memory_write_episode is provided by the Threadwork MCP server (tianqbu/threadwork). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.