How to integrate Linkedin Ads MCP with Autogen

This guide walks you through connecting Linkedin Ads to AutoGen using the Composio tool router. By the end, you'll have a working Linkedin Ads agent that can list active campaigns with daily spend, compare ad performance by campaign objective, create report for sponsored content clicks through natural language commands. This guide will help you understand how to give your AutoGen agent real control over a Linkedin Ads account through Composio's Linkedin Ads MCP server. Before we dive in, let's take a quick look at the key ideas and tools involved.

Get started for free Get a demo

Linkedin Ads

Oauth2

Linkedin Ads is LinkedIn's marketing platform for creating, managing, and measuring paid campaigns across LinkedIn. It helps teams reach professional audiences with precise targeting, campaign analytics, and sponsored content tools.

28 Tools

Managed auth

Connect Linkedin Ads without auth hassles

We manage OAuth, API keys, token refresh, and scopes — you just build.

Try for free

Introduction

This guide will help you understand how to give your AutoGen agent real control over a Linkedin Ads account through Composio's Linkedin Ads MCP server.

Before we dive in, let's take a quick look at the key ideas and tools involved.

Also integrate Linkedin Ads with

OpenAI Agents SDK Claude Agent SDK Claude Code Claude Cowork Codex OpenClaw Hermes CLI Google ADK LangChain Vercel AI SDK Mastra AI LlamaIndex CrewAI

TL;DR

Here's what you'll learn:

Get and set up your OpenAI and Composio API keys
Install the required dependencies for Autogen and Composio
Initialize Composio and create a Tool Router session for Linkedin Ads
Wire that MCP URL into Autogen using McpWorkbench and StreamableHttpServerParams
Configure an Autogen AssistantAgent that can call Linkedin Ads tools
Run a live chat loop where you ask the agent to perform Linkedin Ads operations

What is AutoGen?

Autogen is a framework for building multi-agent conversational AI systems from Microsoft. It enables you to create agents that can collaborate, use tools, and maintain complex workflows.

Key features include:

Multi-Agent Systems: Build collaborative agent workflows
MCP Workbench: Native support for Model Context Protocol tools
Streaming HTTP: Connect to external services through streamable HTTP
AssistantAgent: Pre-built agent class for tool-using assistants

What is the Linkedin Ads MCP server, and what's possible with it?

The Linkedin Ads MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Linkedin Ads account. It provides structured and secure access to your ad accounts, campaign groups, creatives, targeting data, lead forms, and organization content, so your agent can search ad accounts, inspect campaigns, create lead forms, review targeting options, and forecast ad inventory on your behalf.

Ad account discovery and creation: Have your agent search existing ad accounts by status or type, retrieve account details, or create a new ad account.
Campaign and creative review: Let the agent retrieve campaign group details and search your LinkedIn Ads creatives using available filters.
Audience targeting and forecasting: Direct your agent to explore targeting options such as industries, locations, seniorities, job functions, and skills, then check ad inventory forecasts for your planned audience, budget, and bid.
Lead forms and conversion tracking: Instruct your agent to create or retrieve lead generation forms and list the conversion rules connected to an ad account.
Organization content and audience data: Have your agent find LinkedIn organizations, review posting permissions, list organization posts, and inspect available audience segments.

What is the Composio tool router, and how does it fit here?

What is Composio SDK?

Composio's Composio SDK helps agents find the right tools for a task at runtime. You can plug in multiple toolkits (like Gmail, HubSpot, and GitHub), and the agent will identify the relevant app and action to complete multi-step workflows. This can reduce token usage and improve the reliability of tool calls. Read more here: Getting started with Composio SDK

The tool router generates a secure MCP URL that your agents can access to perform actions.

How the Composio SDK works

The Composio SDK follows a three-phase workflow:

Discovery: Searches for tools matching your task and returns relevant toolkits with their details.
Authentication: Checks for active connections. If missing, creates an auth config and returns a connection URL via Auth Link.
Execution: Executes the action using the authenticated connection.

Step-by-step Guide

Step by step08 STEPS

Prerequisites

You will need:

A Composio API key
An OpenAI API key (used by Autogen's OpenAIChatCompletionClient)
A Linkedin Ads account you can connect to Composio
Some basic familiarity with Autogen and Python async

Getting API Keys for OpenAI and Composio

OpenAI API Key

Go to the OpenAI dashboard and create an API key. You'll need credits to use the models, or you can connect to another model provider.
Keep the API key safe.

Composio API Key

Log in to the Composio dashboard.
Navigate to your API settings and generate a new API key.
Store this key securely as you'll need it for authentication.

Install dependencies

bash

pip install composio python-dotenv
pip install autogen-agentchat autogen-ext-openai autogen-ext-tools

Install Composio, Autogen extensions, and dotenv.

What's happening:

composio connects your agent to Linkedin Ads via MCP
autogen-agentchat provides the AssistantAgent class
autogen-ext-openai provides the OpenAI model client
autogen-ext-tools provides MCP workbench support

Set up environment variables

bash

COMPOSIO_API_KEY=your-composio-api-key
OPENAI_API_KEY=your-openai-api-key
USER_ID=your-user-identifier@example.com

Create a .env file in your project folder.

What's happening:

COMPOSIO_API_KEY is required to talk to Composio
OPENAI_API_KEY is used by Autogen's OpenAI client
USER_ID is how Composio identifies which user's Linkedin Ads connections to use

Import dependencies and create Tool Router session

python

import asyncio
import os
from dotenv import load_dotenv
from composio import Composio

from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient
from autogen_ext.tools.mcp import McpWorkbench, StreamableHttpServerParams

load_dotenv()

async def main():
    # Initialize Composio and create a Linkedin Ads session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["linkedin_ads"]
    )
    url = session.mcp.url

What's happening:

load_dotenv() reads your .env file
Composio(api_key=...) initializes the SDK
create(...) creates a Tool Router session that exposes Linkedin Ads tools
session.mcp.url is the MCP endpoint that Autogen will connect to

Configure MCP parameters for Autogen

python

# Configure MCP server parameters for Streamable HTTP
server_params = StreamableHttpServerParams(
    url=url,
    timeout=30.0,
    sse_read_timeout=300.0,
    terminate_on_close=True,
    headers={"x-api-key": os.getenv("COMPOSIO_API_KEY")}
)

Autogen expects parameters describing how to talk to the MCP server. That is what StreamableHttpServerParams is for.

What's happening:

url points to the Tool Router MCP endpoint from Composio
timeout is the HTTP timeout for requests
sse_read_timeout controls how long to wait when streaming responses
terminate_on_close=True cleans up the MCP server process when the workbench is closed

Create the model client and agent

python

# Create model client
model_client = OpenAIChatCompletionClient(
    model="gpt-5",
    api_key=os.getenv("OPENAI_API_KEY")
)

# Use McpWorkbench as context manager
async with McpWorkbench(server_params) as workbench:
    # Create Linkedin Ads assistant agent with MCP tools
    agent = AssistantAgent(
        name="linkedin_ads_assistant",
        description="An AI assistant that helps with Linkedin Ads operations.",
        model_client=model_client,
        workbench=workbench,
        model_client_stream=True,
        max_tool_iterations=10
    )

What's happening:

OpenAIChatCompletionClient wraps the OpenAI model for Autogen
McpWorkbench connects the agent to the MCP tools
AssistantAgent is configured with the Linkedin Ads tools from the workbench

Run the interactive chat loop

python

print("Chat started! Type 'exit' or 'quit' to end the conversation.\n")
print("Ask any Linkedin Ads related question or task to the agent.\n")

# Conversation loop
while True:
    user_input = input("You: ").strip()

    if user_input.lower() in ["exit", "quit", "bye"]:
        print("\nGoodbye!")
        break

    if not user_input:
        continue

    print("\nAgent is thinking...\n")

    # Run the agent with streaming
    try:
        response_text = ""
        async for message in agent.run_stream(task=user_input):
            if hasattr(message, "content") and message.content:
                response_text = message.content

        # Print the final response
        if response_text:
            print(f"Agent: {response_text}\n")
        else:
            print("Agent: I encountered an issue processing your request.\n")

    except Exception as e:
        print(f"Agent: Sorry, I encountered an error: {str(e)}\n")

What's happening:

The script prompts you in a loop with You:
Autogen passes your input to the model, which decides which Linkedin Ads tools to call via MCP
agent.run_stream(...) yields streaming messages as the agent thinks and calls tools
Typing exit, quit, or bye ends the loop

Complete Code

Here's the complete code to get you started with Linkedin Ads and AutoGen:

python

import asyncio
import os
from dotenv import load_dotenv
from composio import Composio

from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient
from autogen_ext.tools.mcp import McpWorkbench, StreamableHttpServerParams

load_dotenv()

async def main():
    # Initialize Composio and create a Linkedin Ads session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["linkedin_ads"]
    )
    url = session.mcp.url

    # Configure MCP server parameters for Streamable HTTP
    server_params = StreamableHttpServerParams(
        url=url,
        timeout=30.0,
        sse_read_timeout=300.0,
        terminate_on_close=True,
        headers={"x-api-key": os.getenv("COMPOSIO_API_KEY")}
    )

    # Create model client
    model_client = OpenAIChatCompletionClient(
        model="gpt-5",
        api_key=os.getenv("OPENAI_API_KEY")
    )

    # Use McpWorkbench as context manager
    async with McpWorkbench(server_params) as workbench:
        # Create Linkedin Ads assistant agent with MCP tools
        agent = AssistantAgent(
            name="linkedin_ads_assistant",
            description="An AI assistant that helps with Linkedin Ads operations.",
            model_client=model_client,
            workbench=workbench,
            model_client_stream=True,
            max_tool_iterations=10
        )

        print("Chat started! Type 'exit' or 'quit' to end the conversation.\n")
        print("Ask any Linkedin Ads related question or task to the agent.\n")

        # Conversation loop
        while True:
            user_input = input("You: ").strip()

            if user_input.lower() in ['exit', 'quit', 'bye']:
                print("\nGoodbye!")
                break

            if not user_input:
                continue

            print("\nAgent is thinking...\n")

            # Run the agent with streaming
            try:
                response_text = ""
                async for message in agent.run_stream(task=user_input):
                    if hasattr(message, 'content') and message.content:
                        response_text = message.content

                # Print the final response
                if response_text:
                    print(f"Agent: {response_text}\n")
                else:
                    print("Agent: I encountered an issue processing your request.\n")

            except Exception as e:
                print(f"Agent: Sorry, I encountered an error: {str(e)}\n")

if __name__ == "__main__":
    asyncio.run(main())

Conclusion

You now have an Autogen assistant wired into Linkedin Ads through Composio's Tool Router and MCP. From here you can:

Add more toolkits to the toolkits list, for example notion or hubspot
Refine the agent description to point it at specific workflows
Wrap this script behind a UI, Slack bot, or internal tool

Once the pattern is clear for Linkedin Ads, you can reuse the same structure for other MCP-enabled apps with minimal code changes.

TOOLS

Supported Tools

Every Linkedin Ads action and event your agent gets out of the box.

Create Ad Account

Tool to create a new LinkedIn ad account for campaign management.

Create Lead Form

Tool to create a new LinkedIn lead generation form for ads.

Get Ad Account

Tool to retrieve a specific LinkedIn Ad Account by ID.

Get Ad Analytics

Tool to retrieve LinkedIn ad analytics and reporting metrics for campaigns, creatives, and accounts.

Get Audience Counts

Get estimated audience size for given targeting criteria on LinkedIn Ads.

Get Campaign Group

Tool to retrieve a specific LinkedIn Ads campaign group by ID.

Get lead form by ID

Tool to retrieve a specific LinkedIn lead form by its ID.

Get organization follower count

Tool to retrieve follower count for a LinkedIn organization.

Get organization access control list

Tool to retrieve organization access control list showing who has admin or poster rights for organizations.

Get organization page statistics

Tool to retrieve page view and click statistics for a LinkedIn organization page.

Get organization follower statistics

Tool to retrieve follower growth statistics for a LinkedIn organization.

Get organization share statistics

Tool to retrieve share and engagement statistics for an organization's content on LinkedIn.

Get Ad Supply Forecasts

Retrieve supply forecasts for LinkedIn ad inventory based on targeting criteria, budget, and bid settings.

Get Targeting Entities

Tool to retrieve targeting entities for LinkedIn Ads campaigns.

Get Targeting Facets

Tool to retrieve available ad targeting facets including industries, locations, seniorities, job functions, skills, and more.

List Conversion Rules

Tool to list all conversion rules for a LinkedIn ad account.

List DMP Segments

Tool to list DMP (Data Management Platform) segments for LinkedIn ad accounts.

List Lead Forms

Tool to list LinkedIn lead forms for an organization or by specific IDs.

List Organizations

Tool to search and list LinkedIn organizations by IDs, vanity name, or parent organization.

List LinkedIn posts

Tool to list LinkedIn posts by author or retrieve multiple posts by IDs.

Lookup organizations

Tool to batch lookup organization details by IDs without requiring admin access.

Tool to register an upload for media assets (images, videos) on LinkedIn.

Search Ad Accounts

Tool to search for LinkedIn ad accounts with filtering by status, type, and test mode.

Search Campaigns

Tool to search and list campaigns in a LinkedIn Ads account with filtering options.

Search LinkedIn Ads Creatives

Tool to search and list LinkedIn Ads creatives with filtering options.

Search Events

Tool to search and list LinkedIn events by organizer with filtering options.

Update lead form

Tool to update an existing LinkedIn lead form.

Update organization access control

Tool to update organization access control for a user on LinkedIn.

FRAMEWORKS

How to build Linkedin Ads MCP Agent with another framework

OpenAI Agents SDK

Use Linkedin Ads MCP with OpenAI Agents SDK

Claude Agent SDK

Use Linkedin Ads MCP with Claude Agent SDK

Claude Code

Use Linkedin Ads MCP with Claude Code

Claude Cowork

Use Linkedin Ads MCP with Claude Cowork

Codex

Use Linkedin Ads MCP with Codex

OpenClaw

Use Linkedin Ads MCP with OpenClaw

Hermes

Use Linkedin Ads MCP with Hermes

CLI

Use Linkedin Ads MCP with CLI

Google ADK

Use Linkedin Ads MCP with Google ADK

LangChain

Use Linkedin Ads MCP with LangChain

Vercel AI SDK

Use Linkedin Ads MCP with Vercel AI SDK

Mastra AI

Use Linkedin Ads MCP with Mastra AI

LlamaIndex

Use Linkedin Ads MCP with LlamaIndex

CrewAI

Use Linkedin Ads MCP with CrewAI

MORE TOOLKITS

Explore Other Toolkits

Toolkit marketplace

Adtraction

Api Key

Adtraction is an affiliate marketing platform for partner programs, tracking links, transactions, commissions, statistics, and payments. It helps advertisers and publishers manage performance marketing with clear reporting and payout workflows.

Bulk Email Checker

Api Key

Bulk Email Checker is an email verification service for checking address validity, mailbox status, domains, and mail-server signals. It helps reduce bounces, spot risky emails, and keep outreach lists cleaner before you send.

Campaign cleaner

Api Key

Campaign cleaner is an email campaign optimization tool that boosts compatibility and deliverability across email clients. It helps marketers get better results by cleaning, enhancing, and ensuring high performance for every campaign.

Deadline funnel

Api Key

Deadline Funnel lets you create personalized deadlines and timers for your marketing campaigns. It helps marketers boost conversions by adding authentic urgency to offers.

FAQ

Frequently asked questions

With a standalone Linkedin Ads MCP server, the agents and LLMs can only access a fixed set of Linkedin Ads tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Linkedin Ads and many other apps based on the task at hand, all through a single MCP endpoint.

Yes, you can. Autogen fully supports MCP integration. You get structured tool calling, message history handling, and model orchestration while Tool Router takes care of discovering and serving the right Linkedin Ads tools.

Yes, absolutely. You can configure which Linkedin Ads scopes and actions are allowed when connecting your account to Composio. You can also bring your own OAuth credentials or API configuration so you keep full control over what the agent can do.

All sensitive data such as tokens, keys, and configuration is fully encrypted at rest and in transit. Composio is SOC 2 Type 2 compliant and follows strict security practices so your Linkedin Ads data and credentials are handled as safely as possible.

Start with Linkedin Ads.It takes 30 seconds.

Managed auth, hosted MCP servers, and every Linkedin Ads tool your agent needs.Free to start.

Start building

Customer stories

Teams ship real agents on Composio

GET STARTED FOR FREE BOOK A DEMO

Karan skipped his own birthday party to fix our critical issue. It was 10pm and he diverted his Waymo to help us instead. This really sets the bar — it shows the commitment you need when users rely on your software.

Harsha Gaddipati

Co-founder, Slashy

A lot of students tell us that the moment their connected tools start talking to each other inside Opennote feels almost magical. The agent just knows them, and it's immensely helped keep new users on the platform.

Abhi Arya

Co-founder, Opennote

We chose Composio over Pipedream because it delivered depth where it mattered — niche tools and tricky edge cases other platforms simply ignored. That gave us confidence to scale without compromising.

Nirman Dave

CEO, Zams

As a solo builder, shipping fast is life or death. The only way I can outcompete incumbents is by outmanoeuvring them. Getting bogged down managing agent auth would have been a death sentence.

Ryan Yu

Founder, Extra Thursday

Before Composio, adding tool integrations was slow and resource-intensive. Each one could take weeks of engineering time, and maintaining them meant constantly keeping up with API changes.

Tomisin Jenrola

Founder & CEO, SwarmZero

With hands-on help from their founder, we integrated Gmail and Google Drive in just 30 minutes. This level of personal support and commitment is exactly what startups should strive for.

Jerome Leclanche

Co-Founder, Ingram Technologies

How to integrate Linkedin Ads MCP with Autogen

Connect Linkedin Ads without auth hassles

Introduction

Also integrate Linkedin Ads with

TL;DR

What is AutoGen?

What is the Linkedin Ads MCP server, and what's possible with it?

What is the Composio tool router, and how does it fit here?

What is Composio SDK?

How the Composio SDK works

Step-by-step Guide

Prerequisites

Getting API Keys for OpenAI and Composio

Install dependencies

Set up environment variables

Import dependencies and create Tool Router session

Configure MCP parameters for Autogen

Create the model client and agent

Run the interactive chat loop

Complete Code

Conclusion

Supported Tools

How to build Linkedin Ads MCP Agent with another framework

OpenAI Agents SDK

Claude Agent SDK

Claude Code

Claude Cowork

Codex

OpenClaw

Hermes

CLI

Google ADK

LangChain

Vercel AI SDK

Mastra AI

LlamaIndex

CrewAI

Explore Other Toolkits

Adtraction

Bulk Email Checker

Campaign cleaner

Deadline funnel

Frequently asked questions

What are the differences in Tool Router MCP and Linkedin Ads MCP?+

Can I use Tool Router MCP with Autogen?+

Can I manage the permissions and scopes for Linkedin Ads while using Tool Router?+

How safe is my data with Composio Tool Router?+

Start with Linkedin Ads.It takes 30 seconds.

Teams ship real agents on Composio