send_direct_message · Networkselfmd MCP: Risk & Policy

WHAT IT DOES

What send_direct_message does on Networkselfmd

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

WHY IT NEEDS A POLICY

Why send_direct_message needs a policy

This tool creates new data (a message) in a reversible manner. It does not execute arbitrary code, delete data permanently, move money, or perform destructive operations.

From the tool's definition Tool description states it 'Send[s] an encrypted direct message' which is a write/create operation that adds data to a communication channel. The tool modifies state by creating a new message record.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

send_direct_message Rate-limited

send_direct_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": {
    "send_direct_message": {
      "limits": [
        {
          "counter": "send_direct_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 Networkselfmd, so you can run agents against it safely.

FAQ

Questions about send_direct_message

What does the send_direct_message tool do? +

Send an encrypted direct message to a specific peer (not through a state). The peer must be online and connected. Get their public key from peer_list. It is categorised as a Write tool in the Networkselfmd MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on send_direct_message? +

Register the Networkselfmd MCP server in PolicyLayer and add a rule for send_direct_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 Networkselfmd. Nothing to install.

What risk level is send_direct_message? +

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

Can I rate-limit send_direct_message? +

Yes. Add a rate_limit block to the send_direct_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 send_direct_message completely? +

Set action: deny in the PolicyLayer policy for send_direct_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 send_direct_message? +

send_direct_message is provided by the Networkselfmd MCP server (selfmd/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.