Linkedin MCP Server logo

Linkedin MCP Server

by fredericbarthelet

This is an MCP server for interacting with the LinkedIn Community Management API. It can be hosted locally or remotely and implements the Draft Third-Party Authorization Flow from MCP specs to delegate authorization to LinkedIn's OAuth authorization server.

View on GitHub

Last updated: N/A

Linkedin MCP Server

MCP server for interacting with Linkedin Community Management API.

This MCP server:

⚠️ Disclaimer: The Third-Party Authorization Flow proposal status is currently in draft. The only MCP client, to my knowledge, that currently implements this specification of the protocol is the MCP Inspector

Features

Tools

  • user-info - Get current logged in user infos (name, headline and profile picture)
  • create-post - Create a new post on LinkedIn

Installation

Follow those instructions to run Linkedin MCP server on your host. You'll need to provide your own Linkedin client.

Requirements

  • Node 22 (lts/jod)
  • pnpm 10
  • a Linkedin client with Community Management API product installed and http://localhost:3001/callback added to the authorized redirect URLs

Instructions

  • Install dependencies:
pnpm install
  • Create env file and populate with your Linkedin client credentials and a random string secret value for JWT_SECRET:
cp .env.template .env && vi .env
  • Run the server:
pnpm run dev
  • Configure your favorite MCP client to use this new server:
{
  "mcpServers": {
    "linkedin": {
      "url": "http://localhost:3001/sse"
    }
  }
}

Debugging

Start the MCP Inspector to debug this server, which is available as a package script:

pnpm run inspector

Access the inspector in your browser at http://localhost:5173

Acknowledgment

  • Den Delimarsky that bravely gave a first shot at this new authorization flow with Microsoft Entra ID and detailed his results in his blog post: https://den.dev/blog/auth-modelcontextprotocol-entra-id/
  • Matt Pocock and his always welcome neat TS tricks specifically in the context of writting your own MCP server on AI Hero: https://www.aihero.dev/publish-your-mcp-server-to-npm