memory_set_working · Threadwork MCP: Risk & Policy

WHAT IT DOES

What memory_set_working does on Threadwork

AI agents use memory_set_working 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_set_working needs a policy

This tool creates or modifies session-scoped working memory without permanent deletion (supports TTL expiry but does not itself delete). It has write semantics but is scoped to a single session and the effects are reversible—new values can overwrite old ones.

From the tool's definition The tool performs an 'upsert' operation on working-memory data with session scope. Upsert is a write operation that creates or modifies data reversibly. The description explicitly states it modifies a key-value store with optional expiry management.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

memory_set_working Rate-limited

memory_set_working 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_set_working": {
      "limits": [
        {
          "counter": "memory_set_working_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_set_working

What does the memory_set_working tool do? +

Upsert a session-scoped working-memory key. Optional ttl_sec sets an expiry timestamp. 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_set_working? +

Register the Threadwork MCP server in PolicyLayer and add a rule for memory_set_working: 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_set_working? +

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

Can I rate-limit memory_set_working? +

Yes. Add a rate_limit block to the memory_set_working 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_set_working completely? +

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

memory_set_working 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.