Skip to main content
All connectors
qbash Connectors / LinkedIn

LinkedIn MCP serverand Python AI tasks

qbash hosts a LinkedIn MCP server you can use in Claude, ChatGPT, Codex, Cursor, Grok Bot and Muse.

Developers use qbash Tasks to write cloud-hosted Python functions that pair LinkedIn with models such as Claude and GPT.

Connect LinkedIn free

MCP server

Build a LinkedIn MCP server

Give ChatGPT, Claude and your other AI tools access to LinkedIn through one server. You pick which LinkedIn tools it shares, and you can add other connectors, memory folders and Tasks to the same server.

How to set it up

  1. Connect LinkedIn on the qbash Connectors page.
  2. Create an MCP server and add the LinkedIn tools you want to share.
  3. Paste the server URL into your client. It connects with OAuth or an access token.

Connect a client Package an MCP server

Python AI task

Write a LinkedIn task in Python

A qbash Task is a hosted Python function that calls LinkedIn and AI models.

Review what your company page has been posting

Read a company page’s 20 most recent posts, then ask an inline prompt to group them by topic and format.

main.py
report = qbash.integrations.linkedin.list_posts(
    author_urn="urn:li:organization:1234567",
    count=20,
    start=0,
)
posts = report.get("posts", [])
if posts:
    review = qbash.ai.run_prompt(
        slug="linkedin-post-themes",
        variables={"posts": json.dumps(posts)},
    )
    qbash.output(review)
else:
    qbash.output("The page has no posts to review.")
Sample list_posts response
{
  "status": "success",
  "posts": [
    {
      "id": "urn:li:share:7251234567890123456",
      "commentary": "Our October release adds scheduled exports. Here is how three customers use them.",
      "created_at": 1792310400000,
      "visibility": "PUBLIC",
      "lifecycle_state": "PUBLISHED"
    }
  ],
  "count": 1
}

What the LinkedIn connector can do

  • Publish text, image, video, document and poll posts
  • List a company page’s recent posts
  • Read impressions, clicks and engagement for page posts
  • Read follower demographics and page view statistics
  • Comment on posts and reply to comments
  • Read analytics for your own member posts
See all 34 LinkedIn methods in the SDK Reference

qbash Tasks: AI applications in Python

A Task is a Python function that calls LinkedIn, your other connectors and models such as Claude, GPT, Gemini and Grok. qbash hosts and runs it.

AnthropicOpenAIGeminixAI

Run Tasks on a schedule or from your team's tools

OpenAIAnthropicGrokGmailSlackGitHub+ more
  • Deterministic where it counts Write the logic in Python and call a model only for the steps that need judgement, so the rest runs the same way every time.
  • Version controlled Every save is a revision you can compare and roll back.
  • Logged Each run records its inputs, output, errors and what started it.
  • Shared credentials Connections belong to your organization, so a Task keeps working when its author is away.

qbash Tasks Python AI SDK

LinkedIn MCP questions

Can the LinkedIn MCP server read posts from my personal profile?

No. LinkedIn has closed the r_member_social permission, so list_posts works for organization pages only. Keep the post URN that create_post returns if you want analytics on a member post later.

How long does a LinkedIn connection last?

LinkedIn access tokens expire after 60 days and cannot be refreshed. Reconnect LinkedIn on the qbash Connectors page when calls start failing with an authentication error.

Do I need my own LinkedIn developer app?

No. You sign in through qbash’s LinkedIn app, which carries Share on LinkedIn and the Community Management API. Page tools need you to be an administrator of that page.

Guides that use LinkedIn

Build a LinkedIn task

Write it in Python with AI steps, and qbash hosts it with versions and run logs.

Build a task

Build a LinkedIn MCP server

Pick the LinkedIn tools to share and connect ChatGPT, Claude or Grok Bot.

Build an MCP server