linkedin_messaging_send_message

WHAT IT DOES

What linkedin_messaging_send_message does on Linkedin

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

WHY IT NEEDS A POLICY

Why linkedin_messaging_send_message needs a policy

Sending a direct message creates new data (the message record) on LinkedIn's platform, making it a Write operation rather than Read. Severity is medium because while messages are reversible (can be deleted), misuse by an unaligned AI agent could enable spam, phishing, or social engineering attacks against the user's professional network.

From the tool's definition Tool is named 'linkedin_messaging_send_message' and description states 'Send direct message (first-degree connections only)'. This creates a new message artifact on LinkedIn's platform.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

linkedin_messaging_send_message Rate-limited

linkedin_messaging_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": {
    "linkedin_messaging_send_message": {
      "limits": [
        {
          "counter": "linkedin_messaging_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 Linkedin, so you can run agents against it safely.

FAQ

Questions about linkedin_messaging_send_message

What does the linkedin_messaging_send_message tool do? +

Send direct message (first-degree connections only). It is categorised as a Write tool in the Linkedin MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on linkedin_messaging_send_message? +

Register the Linkedin MCP server in PolicyLayer and add a rule for linkedin_messaging_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 Linkedin. Nothing to install.

What risk level is linkedin_messaging_send_message? +

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

Can I rate-limit linkedin_messaging_send_message? +

Yes. Add a rate_limit block to the linkedin_messaging_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 linkedin_messaging_send_message completely? +

Set action: deny in the PolicyLayer policy for linkedin_messaging_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 linkedin_messaging_send_message? +

linkedin_messaging_send_message is provided by the Linkedin MCP server (maheidem/linkedin-optimizer-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.