send_linkedin_message · Outx MCP: Risk & Policy

WHAT IT DOES

What send_linkedin_message does on Outx

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

WHY IT NEEDS A POLICY

Why send_linkedin_message needs a policy

This tool creates and stores a new message, which is reversible (messages can be deleted or unsent in most cases). It does not execute arbitrary code, delete data irreversibly, or move money. The 'send' verb indicates a write/create operation.

From the tool's definition Tool description states: 'Send a LinkedIn direct message to a 1st-degree connection.' The action of sending a message creates new data (the message record) in LinkedIn's system and modifies the recipient's message inbox.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

send_linkedin_message Rate-limited

send_linkedin_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_linkedin_message": {
      "limits": [
        {
          "counter": "send_linkedin_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 Outx, so you can run agents against it safely.

FAQ

Questions about send_linkedin_message

What does the send_linkedin_message tool do? +

Send a LinkedIn direct message to a 1st-degree connection. Requires the recipient. It is categorised as a Write tool in the Outx 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_linkedin_message? +

Register the Outx MCP server in PolicyLayer and add a rule for send_linkedin_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 Outx. Nothing to install.

What risk level is send_linkedin_message? +

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

Can I rate-limit send_linkedin_message? +

Yes. Add a rate_limit block to the send_linkedin_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_linkedin_message completely? +

Set action: deny in the PolicyLayer policy for send_linkedin_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_linkedin_message? +

send_linkedin_message is provided by the Outx MCP server (outx-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.