LinkedIn MCP Server

What is LinkedIn MCP Server?

LinkedIn MCP Server is a Model Context Protocol (MCP) server that gives AI assistants access to LinkedIn’s official API. It allows creating posts, managing events, and interacting with LinkedIn through natural language via any MCP‑compatible client. It uses only official endpoints—no scraping or unofficial APIs—so there is no account risk.

How to use LinkedIn MCP Server?

Install Node.js 20+, create a LinkedIn Developer App with the required products (Sign In with LinkedIn OpenID Connect and Share on LinkedIn), and obtain the client ID and secret. Clone the repository, run npm install && npm run build, then configure your MCP client (e.g., Claude Desktop or Claude Code) with the environment variables LINKEDIN_CLIENT_ID and LINKEDIN_CLIENT_SECRET. Once connected, tell your assistant to “Authenticate with LinkedIn” and follow the OAuth flow.

Key features of LinkedIn MCP Server

• Self‑serve OAuth 2.0 authentication with persistent token storage
• Tools for posting, commenting, reacting, deleting, and listing posts
• Event creation and retrieval via LinkedIn’s API
• Local SQLite post‑history tracking for easy reference and deletion
• Adaptive rate limiting and automatic retry with exponential backoff
• Capability detection that only exposes tools matching granted scopes

Use cases of LinkedIn MCP Server

• Post to LinkedIn from natural‑language commands
• Create and manage LinkedIn events through an AI assistant
• View your own LinkedIn profile information (name, headline, photo, email)
• Delete or list your existing LinkedIn posts created via the server
• React to posts with various reactions (like, celebrate, support, love, insightful, funny)

FAQ from LinkedIn MCP Server

How does authentication work?

The server uses OAuth 2.0 with a redirect URI (http://localhost:3000/callback). The assistant generates an authorization URL; you open it in a browser, authorize the app, then copy the redirect URL (which shows a “page not found” error) back to the assistant. The assistant extracts the code and state to complete the flow. The token is stored locally and persists across server restarts for up to 60 days.

What data can the server access?

It can read your own profile and email, create and manage your posts and events, and react to posts. It cannot read others’ profiles, search for people, send messages, read the feed, or access your connections due to LinkedIn API restrictions.

What are the rate limits?

At the development tier, LinkedIn imposes approximately 500 API calls per app per day and about 100 calls per member per day. The server includes adaptive rate limiting that learns actual limits from response headers.

What dependencies are required?

You need Node.js 20+ and a LinkedIn Developer App with the “Sign In with LinkedIn using OpenID Connect” and “Share on LinkedIn” products enabled. The app must have an authorized redirect URL set to http://localhost:3000/callback.

Is there any risk to my LinkedIn account?

No. The server uses only LinkedIn’s official API endpoints—no scraping or unofficial methods are employed. Your account is not at risk as long as you adhere to LinkedIn’s terms.