memory_usage · Claude Flow MCP: Risk & Policy

WHAT IT DOES

What memory_usage does on Claude Flow

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

WHY IT NEEDS A POLICY

Why memory_usage needs a policy

The tool manages coordination memory, which encompasses storing, updating, and retrieving memory entries. The word 'manage' and its replacement tools (store, search, list) suggest it can write/modify memory state. Since it can create or modify data (memory entries), Write is the most appropriate category.

From the tool's definition 'Manage coordination memory' — 'manage' implies read and write operations; deprecated notice references memory/store, memory/search, memory/list as replacements

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

memory_usage Rate-limited

memory_usage 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_usage": {
      "limits": [
        {
          "counter": "memory_usage_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 Claude Flow, so you can run agents against it safely.

FAQ

Questions about memory_usage

What does the memory_usage tool do? +

Manage coordination memory (V2 compatible). Deprecated: Use memory/store, memory/search, or memory/list instead. It is categorised as a Write tool in the Claude Flow 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_usage? +

Register the Claude Flow MCP server in PolicyLayer and add a rule for memory_usage: 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 Claude Flow. Nothing to install.

What risk level is memory_usage? +

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

Can I rate-limit memory_usage? +

Yes. Add a rate_limit block to the memory_usage 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_usage completely? +

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

memory_usage is provided by the Claude Flow MCP server (claude-flow). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.