LinkedIn Publishing

v1.0.0β€’Communicationβ€’stable

πŸ“‡ ☁️ - LinkedIn publishing, commenting, and reacting via Unipile API. Dry-run by default, SKILL.

linkedinllmmcpmodel-context-protocol
Share:
203
Stars
0
Downloads
0
Weekly
0/5

What is LinkedIn Publishing?

LinkedIn Publishing is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to πŸ“‡ ☁️ - linkedin publishing, commenting, and reacting via unipile api. dry-run by default, skill.

πŸ“‡ ☁️ - LinkedIn publishing, commenting, and reacting via Unipile API. Dry-run by default, SKILL.

This server falls under the Communication category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • MCP protocol support

Use Cases

Publish content to LinkedIn
Comment and react to posts
Manage social media presence
adhikasp

Maintainer

LicenseThe Unlicense
Languagepython
Versionv1.0.0
UpdatedMay 21, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

Manual Installation

npx mcp-linkedin

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use LinkedIn Publishing

mcp-linkedin is a Python MCP server that enables AI assistants to publish posts, leave comments, and react to content on LinkedIn via the Unipile API. It operates in dry-run mode by default, showing what would be posted without actually sending anything, making it safe to experiment before going live. Social media managers and developers use it to automate LinkedIn content workflows directly from their AI chat interface.

Prerequisites

  • Python 3.10 or higher
  • A Unipile account with an API key and a connected LinkedIn account
  • The Unipile API endpoint URL for your account
  • An MCP-compatible client such as Claude Desktop or Claude Code CLI
1

Clone the repository

Clone the mcp-linkedin repository from GitHub since it is not published to PyPI.

git clone https://github.com/adhikasp/mcp-linkedin.git
cd mcp-linkedin
2

Install dependencies

Install the Python dependencies using pip or uv into a virtual environment.

python -m venv .venv
source .venv/bin/activate
pip install -r requirements.txt
# Or with uv:
# uv sync
3

Configure Unipile credentials

Set up your Unipile API key and endpoint. The Unipile API acts as the bridge between the MCP server and your LinkedIn account. Obtain these from your Unipile dashboard.

export UNIPILE_API_KEY="your_unipile_api_key"
export UNIPILE_API_ENDPOINT="https://api.unipile.com:13465"
4

Test in dry-run mode

The server defaults to dry-run mode, which logs what would happen without making real LinkedIn API calls. Verify the server starts correctly before connecting it to your MCP client.

python -m mcp_linkedin
5

Add to your MCP client

Register the server in your Claude Desktop config file. Point the command to the Python executable inside your virtual environment.

LinkedIn Publishing Examples

Client configuration

Claude Desktop configuration for mcp-linkedin using the local Python installation.

{
  "mcpServers": {
    "linkedin": {
      "command": "/path/to/mcp-linkedin/.venv/bin/python",
      "args": ["-m", "mcp_linkedin"],
      "env": {
        "UNIPILE_API_KEY": "your_unipile_api_key",
        "UNIPILE_API_ENDPOINT": "https://api.unipile.com:13465"
      }
    }
  }
}

Prompts to try

Example prompts for managing LinkedIn content through the MCP server.

- "Draft and post a LinkedIn update announcing our new product launch"
- "Like and comment on the latest post from [person's name] on LinkedIn"
- "Write a professional LinkedIn post about the benefits of TypeScript (dry-run first)"
- "React to the post with URL https://www.linkedin.com/posts/... with a celebratory reaction"
- "Post a LinkedIn article summary with three bullet points about our Q3 results"

Troubleshooting LinkedIn Publishing

Unipile API returns 401 Unauthorized

Verify that UNIPILE_API_KEY is set correctly and that the key has not expired. Check the Unipile dashboard to ensure your LinkedIn account is still connected and active.

Posts are not appearing on LinkedIn after disabling dry-run mode

Confirm that UNIPILE_API_ENDPOINT matches the endpoint shown in your Unipile account settings (the port number is significant, typically 13465). Also ensure your Unipile plan supports LinkedIn posting.

ModuleNotFoundError when starting the server

Ensure you have activated the virtual environment ('source .venv/bin/activate') or that the Python path in your MCP client config points to the venv's Python executable, not the system Python.

Frequently Asked Questions about LinkedIn Publishing

What is LinkedIn Publishing?

LinkedIn Publishing is a Model Context Protocol (MCP) server that πŸ“‡ ☁️ - linkedin publishing, commenting, and reacting via unipile api. dry-run by default, skill. It connects AI assistants to external tools and data sources through a standardized interface.

How do I install LinkedIn Publishing?

Follow the installation instructions on the LinkedIn Publishing GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with LinkedIn Publishing?

LinkedIn Publishing works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is LinkedIn Publishing free to use?

Yes, LinkedIn Publishing is open source and available under the The Unlicense license. You can use it freely in both personal and commercial projects.

Browse More Communication MCP Servers

Explore all communication servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Quick Config Preview

{ "mcpServers": { "mcp-linkedin": { "command": "npx", "args": ["-y", "mcp-linkedin"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide β†’

Ready to use LinkedIn Publishing?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides