LinkedIn MCP
MCP server for programmable LinkedIn automation via Playwright, offering 20 tools for profile management, messaging, feed interaction, and job searching through real browser automation.
README
<div align="center"> <img src="header.png" alt="LinkedIn MCP Header" width="100%" />
LinkedIn MCP Server
Programmable LinkedIn Automation via Playwright and the Model Context Protocol.
📌 Overview
This MCP server exposes LinkedIn as a programmable platform via Playwright browser automation. It provides 20 strictly typed tools across profile management, connections, messaging, feed interaction, and job searching. All interactions are driven by automating a real Chromium browser against LinkedIn's web UI, entirely bypassing unofficial APIs.
🏗️ Architecture
graph TD
Host[MCP Host / Claude Desktop] <-->|JSON-RPC over stdio| MCP[LinkedIn MCP Node.js Server]
subgraph Core Automation Engine
MCP --> SessionMgr[Session & Cookie Manager]
MCP --> Tools[20 Typed Action Tools]
Tools --> Playwright[Playwright API]
end
Playwright -->|CDP Commands| Chrome[Non-Headless Chromium]
Chrome <-->|Web Traffic| LI[(LinkedIn Web Platform)]
🚀 Getting Started
Prerequisites
- Node.js 20+
- A LinkedIn Account
- Environment configuration
Setup
# Install dependencies
npm install
# Build the project
npm run build
# Configure environment
cp .env.example .env
Edit your .env to include dummy/example credentials or your real credentials if deploying locally:
LINKEDIN_EMAIL=example@example.com
LINKEDIN_PASSWORD=your_password
COOKIES_PATH=./linkedin_cookies.json
(Note: Session cookies are persisted automatically after the first successful login).
🛠️ Tool Ecosystem
👤 Profile Tools
get_my_profile/get_my_profile_fullget_person_profile/get_person_profile_full
✏️ Profile Editing (ProseMirror compatible)
update_profile_text/edit_headlineadd_experience_block/add_skill
🤝 Networking Pipeline
search_people/connect_with_personsmart_connect: Autonomous multi-phase networking pipeline (Scrape -> Search -> Score -> Reach Out).
💬 Messaging & Feed
get_inbox/send_messageget_feed/get_company_posts/create_post
💼 Job Search
search_jobs/get_job_details
⚙️ Technical Highlights
- Anti-Bot Circumvention: Utilizes non-headless Chromium instances to mimic legitimate user interaction.
- ProseMirror Handlers: Gracefully handles LinkedIn's complex TipTap/ProseMirror rich-text editors for post creation and profile updates.
- Dry-Run Safety: All mutating endpoints support a
dryRunboolean, executing form logic while bypassing the final submit action. - Session Resilience: Implements automated login detection and session recovery loops with explicit CAPTCHA abortion.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.