teammate_save_memory · Claude Flow MCP: Risk & Policy

WHAT IT DOES

What teammate_save_memory does on Claude Flow

AI agents use teammate_save_memory 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 teammate_save_memory needs a policy

This tool writes or persists session memory to storage, which is a reversible data modification operation. It does not retrieve data (Read), execute arbitrary code or external operations (Execute), permanently delete data (Destructive), or involve financial transactions (Financial).

From the tool's definition Tool name 'teammate_save_memory' and description 'Save teammate session memory to disk' indicate creation/modification of persistent data via writing to disk.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

teammate_save_memory Rate-limited

teammate_save_memory 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": {
    "teammate_save_memory": {
      "limits": [
        {
          "counter": "teammate_save_memory_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 teammate_save_memory

What does the teammate_save_memory tool do? +

Save teammate session memory to disk. 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 teammate_save_memory? +

Register the Claude Flow MCP server in PolicyLayer and add a rule for teammate_save_memory: 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 teammate_save_memory? +

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

Can I rate-limit teammate_save_memory? +

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

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

teammate_save_memory 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.