How to integrate Linkedin MCP with Autogen

Trusted by
AWS
Glean
Zoom
Airtable
GET STARTED FOR FREEGET A DEMO

30 min · no commitment · see it on your stack

Linkedin logo
AutoGen logo
divider

Introduction

This guide walks you through connecting Linkedin to AutoGen using the Composio tool router. By the end, you'll have a working Linkedin agent that can share a new post about our product launch, delete your last published linkedin post, fetch company pages i can manage through natural language commands.

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

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

Also integrate Linkedin with

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
  • Wire that MCP URL into Autogen using McpWorkbench and StreamableHttpServerParams
  • Configure an Autogen AssistantAgent that can call Linkedin tools
  • Run a live chat loop where you ask the agent to perform Linkedin 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 MCP server, and what's possible with it?

The Linkedin 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 account. It provides structured and secure access to your LinkedIn profile and company pages, so your agent can post updates, fetch your profile, manage company info, and even delete posts on your behalf.

  • Automated LinkedIn posting: Let your agent create and share new posts from your profile or managed company pages, keeping your network engaged without manual effort.
  • Profile information retrieval: Instantly fetch your LinkedIn profile details, including author ID and headline, for use in resumes, reporting, or personalized content generation.
  • Company page management: Retrieve a list of organizations you manage, making it easy for your agent to post or gather company info for employer branding and outreach.
  • Content cleanup and moderation: Direct your agent to delete specific LinkedIn posts (by share ID) to maintain a professional, up-to-date presence.

Supported Tools & Triggers

Tools
Create article or URL shareTool to create an article or URL share on LinkedIn using the UGC Posts API.
Create comment on LinkedIn postTool to create a first-level or nested comment on a LinkedIn share, UGC post, or parent comment via the Social Actions Comments API.
Create a LinkedIn postCreates a new post on LinkedIn for the authenticated user or an organization they manage.
Delete LinkedIn PostDeletes a specific LinkedIn post (share) by its unique `share_id`, which must correspond to an existing share.
Delete PostDelete a LinkedIn post using the Posts API REST endpoint.
Delete UGC Post (Legacy)Delete a UGC post using the legacy UGC Post API endpoint.
Get ad targeting facetsTool to retrieve available ad targeting facets from LinkedIn Marketing API.
Get audience countsRetrieves audience size counts for specified targeting criteria.
Get company infoRetrieves organizations where the authenticated user has specific roles (ACLs), to determine their management or content posting capabilities for LinkedIn company pages.
Get image detailsTool to retrieve details of a LinkedIn image using its URN.
Get imagesTool to retrieve image metadata including download URLs, status, and dimensions from LinkedIn's Images API.
Get my infoFetches the authenticated LinkedIn user's profile information including name, headline, profile picture, and other profile details.
Get network sizeTool to retrieve the follower count for a LinkedIn organization.
Get organization page statisticsTool to retrieve page statistics for a LinkedIn organization page.
Get person profileRetrieves a LinkedIn member's profile information by their person ID.
Get post contentTool to retrieve detailed post content including text, images, videos, and metadata from LinkedIn by post URN.
Get share statisticsRetrieves share statistics for a LinkedIn organization, including impressions, clicks, likes, comments, and shares.
Get videosRetrieves video metadata from LinkedIn Marketing API.
Initialize image uploadTool to initialize an image upload to LinkedIn and return a presigned upload URL plus the resulting image URN.
List reactions on entityRetrieves reactions (likes, celebrations, etc.
Register image uploadTool to initialize a native LinkedIn image upload for feed shares and return a presigned upload URL plus the resulting digital media asset URN.
Search ad targeting entitiesSearch for ad targeting entities using typeahead search.

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:

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

Step-by-step Guide

Prerequisites

You will need:

  • A Composio API key
  • An OpenAI API key (used by Autogen's OpenAIChatCompletionClient)
  • A Linkedin 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 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 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 session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["linkedin"]
    )
    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 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 assistant agent with MCP tools
    agent = AssistantAgent(
        name="linkedin_assistant",
        description="An AI assistant that helps with Linkedin 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 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 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 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 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 session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["linkedin"]
    )
    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 assistant agent with MCP tools
        agent = AssistantAgent(
            name="linkedin_assistant",
            description="An AI assistant that helps with Linkedin 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 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 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, you can reuse the same structure for other MCP-enabled apps with minimal code changes.

How to build Linkedin MCP Agent with another framework

ChatGPT logo

ChatGPT

Use Linkedin MCP with ChatGPT

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Linkedin MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Linkedin MCP with Claude Agent SDK

Claude Code logo

Claude Code

Use Linkedin MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Linkedin MCP with Claude Cowork

Codex logo

Codex

Use Linkedin MCP with Codex

Cursor logo

Cursor

Use Linkedin MCP with Cursor

OpenClaw logo

OpenClaw

Use Linkedin MCP with OpenClaw

Hermes logo

Hermes

Use Linkedin MCP with Hermes

CLI logo

CLI

Use Linkedin MCP with CLI

Google ADK logo

Google ADK

Use Linkedin MCP with Google ADK

LangChain logo

LangChain

Use Linkedin MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use Linkedin MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use Linkedin MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Linkedin MCP with LlamaIndex

CrewAI logo

CrewAI

Use Linkedin MCP with CrewAI

OpenCode logo

OpenCode

Use Linkedin MCP with OpenCode

VS Code logo

VS Code

Use Linkedin MCP with VS Code

FAQ

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

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

Can I use Tool Router MCP with Autogen?

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 tools.

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

Yes, absolutely. You can configure which Linkedin 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.

How safe is my data with Composio Tool Router?

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 data and credentials are handled as safely as possible.

Used by agents from

Context
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai

Never worry about agent reliability

We handle tool reliability, observability, and security so you never have to second-guess an agent action.

Get started for freeGet a demo↗