LinkedIn Browser
A FastMCP-based server that enables programmatic LinkedIn automation and data extraction through browser automation, offering secure authentication and tools for profile operations and post interactions while respecting LinkedIn's rate limits.
What is LinkedIn Browser?
LinkedIn Browser is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to fastmcp-based server that enables programmatic linkedin automation and data extraction through browser automation, offering secure authentication and tools for profile operations and post interactions...
A FastMCP-based server that enables programmatic LinkedIn automation and data extraction through browser automation, offering secure authentication and tools for profile operations and post interactions while respecting LinkedIn's rate limits.
This server falls under the Browser Automation category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- A FastMCP-based server that enables programmatic LinkedIn au
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx linkedin-browser-mcp-serverConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use LinkedIn Browser
LinkedIn Browser MCP Server is a FastMCP-based server that automates LinkedIn interactions through Playwright browser automation, exposing tools for profile searching, profile viewing, feed browsing, and post engagement to AI assistants. It manages authentication via encrypted session cookies to minimise repeated logins and enforces built-in rate limiting to stay within LinkedIn's usage policies. Recruiters, researchers, and growth teams use it to extract structured LinkedIn data and automate routine profile operations through natural language.
Prerequisites
- Python 3.8+ with pip and venv
- Playwright installed and Chromium browser downloaded (playwright install chromium)
- A LinkedIn account with valid credentials
- An MCP-compatible client such as Claude Desktop
- Optional: a COOKIE_ENCRYPTION_KEY (auto-generated if omitted)
Clone the repository
Clone the mcp-linkedin-server repository to your local machine and change into the project directory.
git clone https://github.com/alinaqi/mcp-linkedin-server.git
cd mcp-linkedin-serverCreate a virtual environment and install dependencies
Set up an isolated Python environment, activate it, install requirements, and download the Chromium browser binary that Playwright uses.
python -m venv env
source env/bin/activate
pip install -r requirements.txt
playwright install chromiumConfigure environment variables
Create a .env file in the project root with your LinkedIn credentials. The COOKIE_ENCRYPTION_KEY is optional and will be auto-generated on first run if not supplied.
[email protected]
LINKEDIN_PASSWORD=your_password
COOKIE_ENCRYPTION_KEY=your_optional_encryption_keyStart the server to verify it works
Run the server script directly to confirm it starts without errors. It will launch a Chromium browser and attempt to log in to LinkedIn.
python linkedin_browser_mcp.pyConfigure your MCP client
Add the server to claude_desktop_config.json pointing to the Python executable in your virtual environment and the server script.
{
"mcpServers": {
"linkedin-browser": {
"command": "/path/to/mcp-linkedin-server/env/bin/python",
"args": ["/path/to/mcp-linkedin-server/linkedin_browser_mcp.py"],
"env": {
"LINKEDIN_USERNAME": "[email protected]",
"LINKEDIN_PASSWORD": "your_password"
}
}
}
}LinkedIn Browser Examples
Client configuration
Claude Desktop config that runs the LinkedIn browser server using the project's virtual environment Python.
{
"mcpServers": {
"linkedin-browser": {
"command": "/path/to/mcp-linkedin-server/env/bin/python",
"args": ["/path/to/mcp-linkedin-server/linkedin_browser_mcp.py"],
"env": {
"LINKEDIN_USERNAME": "[email protected]",
"LINKEDIN_PASSWORD": "your_password"
}
}
}
}Prompts to try
Sample prompts that exercise the LinkedIn browser tools.
- "Log in to LinkedIn and browse my feed, summarizing the top 5 posts."
- "Search LinkedIn for software engineers in Berlin and list the top 10 profiles."
- "View the LinkedIn profile at https://www.linkedin.com/in/someusername and extract their current role and skills."
- "Like the most recent post from my LinkedIn feed."
- "Comment 'Great insights!' on the first post in my feed."Troubleshooting LinkedIn Browser
Login fails with a CAPTCHA or security challenge from LinkedIn
LinkedIn may prompt for human verification on new logins. Log in manually in a Chromium browser first, copy the session cookies to the encrypted cookie store, or reduce the login frequency by reusing saved sessions.
Playwright raises 'Executable not found' for Chromium
Run 'playwright install chromium' inside the activated virtual environment. If using a system Python, ensure the playwright package's browser path is on the PATH.
Rate limit errors or account restrictions from LinkedIn
The server enforces a maximum of 5 login attempts per hour. Avoid running bulk operations in rapid succession. Reuse the saved cookie session instead of logging in repeatedly.
Frequently Asked Questions about LinkedIn Browser
What is LinkedIn Browser?
LinkedIn Browser is a Model Context Protocol (MCP) server that fastmcp-based server that enables programmatic linkedin automation and data extraction through browser automation, offering secure authentication and tools for profile operations and post interactions while respecting linkedin's rate limits. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install LinkedIn Browser?
Follow the installation instructions on the LinkedIn Browser GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with LinkedIn Browser?
LinkedIn Browser works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is LinkedIn Browser free to use?
Yes, LinkedIn Browser is open source and available under the MIT license. You can use it freely in both personal and commercial projects.
LinkedIn Browser Alternatives — Similar Browser Automation Servers
Looking for alternatives to LinkedIn Browser? Here are other popular browser automation servers you can use with Claude, Cursor, and VS Code.
Chrome DevTools MCP
★ 40.6kAI-powered Chrome automation server with natural language element detection. Control Chrome browser through MCP protocol for testing, debugging, and performance analysis. Features 91% accuracy in element location, works with free AI models, and suppo
UI TARS Desktop
★ 34.9k📇 🏠 - Browser automation capabilities using Puppeteer, both support local and remote browser connection.
Playwright
★ 32.8kA production-ready browser automation server that enables AI assistants to interact with web pages using tools for navigation, element interaction, and data extraction. It features a built-in Inspector UI and robust crash recovery for reliable automa
Page Agent
★ 18.0kJavaScript in-page GUI agent. Control web interfaces with natural language.
Chrome
★ 11.7kAn extension-based MCP server that enables AI assistants to control your browser, leveraging existing sessions and login states for automation and content analysis. It provides over 20 tools for semantic tab search, interactive element manipulation,
LAMDA
★ 7.8kThe most powerful Android RPA agent framework, next generation mobile automation.
Browse More Browser Automation MCP Servers
Explore all browser automation servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up LinkedIn Browser in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use LinkedIn Browser?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.