trackmcp
Back to directory
FilippTrigub

linkedin-mcp

View on GitHub

An MCP server to use the LinkedIn API.

10 stars PythonOthers Updated Jul 5, 2026

Documentation

LinkedIn MCP Server

Post to LinkedIn directly from Claude Desktop with support for text and media attachments.

Features

  • Post text updates to LinkedIn
  • Attach images and videos to posts
  • Control post visibility (public/connections)
  • OAuth2 authentication flow
  • Secure token storage

Tools

  • `authenticate`: Authenticate with LinkedIn
  • `create_post`: Create and share posts optionally with media attachments
    • state the file path to the relevant media file to attach it to the post

Setup

1. Create a LinkedIn Developer App:

code
Visit https://www.linkedin.com/developers/apps
   Create new app
   Add product permissions: Log In to LinkedIn and Share on LinkedIn 
   Configure OAuth redirect URL: http://localhost:3000/callback

2. Install

Install `pipx` if not already installed

bash
pip install pipx

Install linkedin-mcp

bash
pipx install linkedin-mcp

3. Create `.env` file:

env
LINKEDIN_CLIENT_ID=your_client_id
   LINKEDIN_CLIENT_SECRET=your_client_secret
   LINKEDIN_REDIRECT_URI=http://localhost:3000/callback

Claude Desktop Configuration

Add the following configuration to `claude-desktop.json`:

json
{
  "mcpServers": {
    "linkedin-mcp": {
      "command": "linkedin-mcp",
      "env": {
        "LINKEDIN_CLIENT_ID": "",
        "LINKEDIN_CLIENT_SECRET": "",
        "LINKEDIN_REDIRECT_URI": ""
      }
    }
  }
}

Development

Clone the repository and install the package in editable mode:

bash
git clone https://github.com/FilippTrigub/linkedin-mcp.git
   cd linkedin-mcp
   uv venv

Run the server from development directory:

json
{
  "mcpServers": {
    "linkedin-mcp": {
       "command": "uv",
      "args": [
        "--directory",
        "absolute\\path\\to\\linkedin-mcp",
        "run",
        "-m",
        "linkedin_mcp.server"
      ],
      "env": {
        "LINKEDIN_CLIENT_ID": "",
        "LINKEDIN_CLIENT_SECRET": "",
        "LINKEDIN_REDIRECT_URI": ""
      }
    }
  }
}

License

MIT License

Frequently asked questions

What is linkedin-mcp?

linkedin-mcp is An MCP server to use the LinkedIn API.

How do I install linkedin-mcp?

Open the GitHub repository and follow its README. Most MCP servers are added to your client's MCP config, then called by your agent.

Is linkedin-mcp open source?

Yes — it is hosted on GitHub at https://github.com/FilippTrigub/linkedin-mcp and has 10 stars.

Related MCP tools

topoteretescognee

Cognee is the open-source AI memory platform for agents. Give your AI agents persistent long-term memory across sessions with a self-hosted knowledge graph engine.

30,433 Python
agent-memoryagent-skillsai+16
Skyvern-AIskyvern

Automate browser based workflows with AI

22,930 Python
apiautomationbrowser+13
vectorize-iohindsight

Hindsight: Agent Memory That Learns

22,468 Python
agentic-aimemoryagents+1
guillaumemeyerwatermarks-remover

A privacy-first app that strips AI watermarks from content you own.

20,504 Python
agent-skillaic2pa+12
QwenLMQwen-Agent

Agent framework and applications built upon Qwen>=3.0, featuring Function Calling, MCP, Code Interpreter, RAG, Chrome extension, etc.

17,062 Python
BeehiveInnovationspal-mcp-server

The power of Claude Code / GeminiCLI / CodexCLI + [Gemini / OpenAI / OpenRouter / Azure / Grok / Ollama / Custom Model / All Of The Above] working as one.

11,731 Python

Run your own MCP server? See who uses it and what to fix.

Measure it with TrackMCP