linkedin.passthrough.write · Ads MCP: Risk & Policy

WHAT IT DOES

What linkedin.passthrough.write does on Ads

AI agents invoke linkedin.passthrough.write to trigger actions in Ads. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why linkedin.passthrough.write needs a policy

This is a catch-all passthrough tool that can execute arbitrary POST, PARTIAL_UPDATE, or DELETE operations against any LinkedIn REST endpoint. Because it spans Write, Destructive, and potentially Financial operations (e.g., modifying budgets or campaigns), and its effects depend entirely on the endpoint and payload provided, Execute is the highest applicable non-Financial category.

From the tool's definition POST/PARTIAL_UPDATE/DELETE any LinkedIn /rest endpoint

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

linkedin.passthrough.write Rate-limited

linkedin.passthrough.write stays usable, but rate-capped — a runaway agent can't fire it dozens of times 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.passthrough.write": {
      "limits": [
        {
          "counter": "linkedin.passthrough.write_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Ads, so you can run agents against it safely.

FAQ

Questions about linkedin.passthrough.write

What does the linkedin.passthrough.write tool do? +

Fallback: POST/PARTIAL_UPDATE/DELETE any LinkedIn /rest endpoint. Use only when no named tool exists. Prefer linkedin.campaigns.pause/resume/update_budget, linkedin.creatives.pause/resume. Requires confirm_passthrough=true. Dry-run by default. It is categorised as a Execute tool in the Ads MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on linkedin.passthrough.write? +

Register the Ads MCP server in PolicyLayer and add a rule for linkedin.passthrough.write: 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 Ads. Nothing to install.

What risk level is linkedin.passthrough.write? +

linkedin.passthrough.write is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit linkedin.passthrough.write? +

Yes. Add a rate_limit block to the linkedin.passthrough.write 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.passthrough.write completely? +

Set action: deny in the PolicyLayer policy for linkedin.passthrough.write. 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.passthrough.write? +

linkedin.passthrough.write is provided by the Ads MCP server (manlikemuneeb/ads-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.