How to Use the LinkedIn Ads MCP in OpenAI Agents SDK

Q: How do I trace LinkedIn Ads tool calls in the OpenAI Agents SDK?

The SDK automatically forwards all tool calls, including getcampaignanalytics payloads, to your central developer console. You can inspect the raw inputs and response latency for every single tool execution in real-time.

Control LinkedIn Ads budgets and pause underperforming campaigns safely in production using OpenAI Agents SDK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect LinkedIn Ads MCP to OpenAI Agents SDK

Create your Vinkius account to connect LinkedIn Ads to OpenAI Agents SDK and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup LinkedIn Ads with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Guardrail-protected LinkedIn Ads budget control

The LinkedIn Ads MCP Server exposes `pause_campaign` and `enable_campaign` directly to your production Python agents. Look, the reality is that your agent shouldn't have free rein over your credit card. By defining strict execution guardrails in your OpenAI Agents SDK configuration, you prevent your agent from making unauthorized budget changes or pausing high-performing ad sets without human sign-off. You configure these campaign execution boundaries programmatically in Python to monitor ad spend. When your agent decides to trigger `pause_campaign` based on real-time performance drops, the SDK intercepts the payload, runs your validation logic, and logs the pre-execution state to your dashboard.

Multi-agent handoffs for deep B2B analysis

The LinkedIn Ads MCP Server allows you to partition tasks between specialized agents in your OpenAI Agents SDK workflow. You can deploy a lightweight analyst agent that polls `get_campaign_analytics` and `get_account_analytics` continuously without wasting token overhead on heavy reasoning models. Let's look at the numbers. If your analyst agent identifies high-cost LinkedIn clicks, it hands off the execution context to a senior bidding agent. This specialized agent then calls `list_creatives` to inspect the active assets and determines if a creative refresh is required.

Full tracing of MCP Server calls in OpenAI

The LinkedIn Ads MCP Server integrates directly with your OpenAI Agents SDK tracing dashboard to record every API interaction. Every single call to `list_campaigns` or `list_campaign_groups` is logged with exact payload inputs, response times, and token usage. This transparency eliminates the guesswork when debugging complex multi-agent LinkedIn campaign optimizations. You see exactly why your agent queried `get_account_info` and can trace the decision tree that led to an automated campaign modification.

Setup guide

Set up LinkedIn Ads MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all LinkedIn Ads tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives LinkedIn Ads tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate LinkedIn Ads tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="LinkedIn Ads Agent",
            instructions="You have access to LinkedIn Ads tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by LinkedIn Ads. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect LinkedIn Ads now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about LinkedIn Ads MCP in OpenAI Agents SDK

Install the core agents package and initialize the server HTTP parameters with your Vinkius endpoint token. Pass the server instance inside the server parameter list when instantiating your agent. The SDK automatically registers tools like `list_campaigns` for your agent to use immediately.

Yes, you can write custom Python guardrails to intercept the `enable_campaign` tool before execution. This ensures the model never activates campaigns that exceed your specific budget thresholds, keeping your spend completely secure.

The SDK automatically forwards all tool calls, including `get_campaign_analytics` payloads, to your central developer console. You can inspect the raw inputs and response latency for every single tool execution in real-time.

No, the OpenAI framework auto-discovers all eight campaign management and analytics tools from the schema at runtime. You only need to point the SDK to your Vinkius HTTP URL.

Your LinkedIn Ads account info, campaign metrics, and creative assets never touch external caching layers. Vinkius runs the server in an ephemeral, zero-trust V8 sandbox that only passes raw JSON tool outputs directly to your local SDK runtime over an encrypted connection.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript