linkedin_publishLABSCO SUMMARY
Publishing with the preview step built in.
The assistant writes the post and Unipile does the actual publishing. Because preview is the default, the failure mode of an over-eager model is a draft you reject rather than something already on your feed.
What it is
An MCP server over the Unipile API that publishes to LinkedIn on your behalf. The assistant writes the post or comment; this handles the publishing, with media attachments and company mentions supported, and every publishing action defaulting to preview mode.
What you get
- A post published to LinkedIn from text the assistant wrote (linkedin_publish)
- A comment posted on a LinkedIn post (linkedin_comment)
- Preview by default: publishing actions are a dry run until you confirm them
- Media attachments from local files or URLs, images and video
- Company mentions resolved automatically through Unipile
- Posts auto-liked immediately after publishing
Requirements
Node.js 18+ and a clone with npm install, plus a Unipile account with your LinkedIn connected. The Unipile API key and DSN go in the MCP config rather than a .env file, and the client needs restarting after the edit.
Setup effort
Build from source — git clone https://github.com/timkulbaev/mcp-linkedin.git
USE CASES
01
Getting a post out without opening LinkedIn
The text is written and published in one place, with an image or video attached from a local file or a URL.
02
Seeing exactly what will go live first
Publishing actions run as a preview by default, so the wording, the attachment and the mentions are all checked before anything is posted.
03
Replying to something in your feed
A comment is posted on an existing LinkedIn post, so a response written with the assistant lands where the conversation is.
04
Mentioning a company correctly
Company mentions are resolved through Unipile, which is what makes the tag link to the actual page rather than sitting there as plain text.
3 tools
Listed in project docs. Your client may show a different list.
linkedin_commentlinkedin_reactBEFORE YOU INSTALL
What to know first
Tools you get
3 tools named in the project's documentation.
Requires
- Node.js 18+
- UNIPILE_API_KEY in your environment
- UNIPILE_DSN in your environment
Where it runs
Both documented clients run the server on your machine.
INSTALLATION
Connect your client
Server setup
TERMINAL
git clone https://github.com/timkulbaev/mcp-linkedin.git
cd mcp-linkedin
npm installMCP Clients
Claude Code, Claude Desktop
JSON
{
"mcpServers": {
"linkedin": {
"command": "node",
"args": [
"<YOUR_PATH_TO_MCP_LINKEDIN>/index.js"
],
"env": {
"UNIPILE_API_KEY": "<YOUR_UNIPILE_API_KEY>",
"UNIPILE_DSN": "<YOUR_UNIPILE_DSN>"
}
}
}
}
