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)
コメント