memory_send_message · Junto Memory MCP: Risk & Policy

WHAT IT DOES

What memory_send_message does on Junto Memory

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

WHY IT NEEDS A POLICY

Why memory_send_message needs a policy

An AI agent can call memory_send_message faster than any human can review — one bad instruction and it creates or modifies resources in Junto Memory by the hundred, each call as confident as the last.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

memory_send_message Rate-limited

memory_send_message 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_send_message": {
      "limits": [
        {
          "counter": "memory_send_message_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 Junto Memory, so you can run agents against it safely.

FAQ

Questions about memory_send_message

What does the memory_send_message tool do? +

memory_send_message. It is categorised as a Write tool in the Junto Memory 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_send_message? +

Register the Junto Memory MCP server in PolicyLayer and add a rule for memory_send_message: 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 Junto Memory. Nothing to install.

What risk level is memory_send_message? +

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

Can I rate-limit memory_send_message? +

Yes. Add a rate_limit block to the memory_send_message 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_send_message completely? +

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

memory_send_message is provided by the Junto Memory MCP server (tlemmons/junto-memory). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.