How to Use the LinkedIn MCP in OpenAI Agents SDK

Q: Can an OpenAI Agents SDK agent manage multiple LinkedIn company pages?

Yes, the OpenAI Agents SDK agent uses listorganizations to find every page you admin on LinkedIn. From there, it can query specific details with getorganization to decide where to publish.

Run production-grade OpenAI Agents SDK workflows to post updates and manage companies on LinkedIn without manual API calls.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect LinkedIn MCP to OpenAI Agents SDK

Create your Vinkius account to connect LinkedIn 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 with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Auto-publish LinkedIn updates with OpenAI Agents SDK

The `create_post` tool lets your OpenAI Agents SDK agent publish updates directly to your feed. Pass this LinkedIn MCP Server to your agent constructor, and let the model determine when to trigger the post based on your raw content drafts. The OpenAI Agents SDK automatically discovers the tool, meaning you write zero glue code to get text onto your LinkedIn feed. You get built-in safety constraints directly from the OpenAI Agents SDK when publishing. Before the model fires off a live LinkedIn post, your supervisor agent validates the payload against your brand guidelines. If it passes, the agent executes the tool and returns the live post ID instantly.

Audit your managed organizations on the fly

You can audit your corporate pages using the `list_organizations` tool within the OpenAI Agents SDK. Managing multiple corporate pages gets messy fast, but the SDK handles the complexity. Your agent can fetch every LinkedIn entity where you have admin rights, then drill down into specific profiles using `get_organization`. Because the OpenAI Agents SDK tracks agent handoffs, you can have one specialist agent pull the LinkedIn company list and hand it to a writer agent. That writer agent then drafts tailored updates for each company, keeping your brand voices completely separate and clean.

Verify user identities for secure workflows

The `get_me` tool verifies the active user's identity before executing any automated OpenAI Agents SDK tasks. Before letting an autonomous agent run wild on LinkedIn, you need to know whose account it is using. The agent calls `get_email` to verify the authenticated user's LinkedIn profile data and primary email address. This verification step prevents your OpenAI Agents SDK agent from publishing to the wrong personal profile. It acts as a hard runtime boundary, logging the active user's LinkedIn credentials to your OpenAI tracing dashboard before any social actions execute on this MCP Server.

Setup guide

Set up LinkedIn 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 tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives LinkedIn 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 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 Agent",
            instructions="You have access to LinkedIn 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. 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 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 MCP in OpenAI Agents SDK

Install the package and initialize MCPServerStreamableHttp with your Vinkius endpoint. Pass this server instance in the mcp_servers list when creating your OpenAI Agents SDK Agent. The agent automatically registers LinkedIn tools like `create_post` and starts using them.

Yes, the OpenAI Agents SDK agent uses `list_organizations` to find every page you admin on LinkedIn. From there, it can query specific details with `get_organization` to decide where to publish.

Yes, you should set cacheToolsList=True in your streamable HTTP parameters for OpenAI Agents SDK. This prevents the SDK from repeatedly fetching the LinkedIn tool definitions from the MCP Server, keeping response times fast.

You can set up a validation agent in OpenAI Agents SDK that checks the output of `create_post`. If the LinkedIn tool returns an error, the agent can catch it, analyze the failure reason, and retry with corrected formatting.

All LinkedIn profile info, email addresses, and post content stay inside your OpenAI Agents SDK runtime. Vinkius runs the server in a sandboxed V8 Isolate, meaning your OAuth tokens and raw text are never stored or logged on our end.

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