linkedin-mcp-server

Overview

The LinkedIn MCP server by stickerdaniel is a Python-based implementation that connects AI assistants to LinkedIn through controlled browser sessions. It provides comprehensive access to LinkedIn features including profile retrieval, company information, job searches, and messaging capabilities. The server operates by controlling a real browser session rather than using undocumented APIs, with tool calls executed sequentially via a queue system.

Try asking AI

After installing, here are 5 things you can ask your AI assistant:

• get_person_profile

  Get profile info with explicit section selection (experience, education, interests, honors, languages, certifications, skills, projects, contact_info, posts)

  Try:Get John Doe's profile focusing on experience and educationTry:Show me the skills section of Sarah Smith's profile
• get_my_profile

  Get the authenticated user's own LinkedIn profile (same sections as get_person_profile)

  Try:Get my own profile with all sectionsTry:Show me my experience and education from my LinkedIn profile
• connect_with_person

  Send a connection request or accept an incoming one, with optional note

  Try:Send a connection request to Jane Doe with note 'We met at the conference'Try:Accept connection request from John Smith
• get_sidebar_profiles

  Extract profile URLs from sidebar recommendation sections ('More profiles for you', 'Explore premium profiles', 'People you may know') on a profile page

  Try:Get recommended profiles from the sidebarTry:Extract 'People you may know' profile URLs
• get_inbox

  List recent conversations from the LinkedIn messaging inbox

  Try:Show me my recent LinkedIn conversationsTry:List messages in my inbox
• get_conversation

  Read a specific messaging conversation by username or thread ID

  Try:Get conversation with Jane DoeTry:Show me messages from thread ID 12345
• search_conversations

  Search messages by keyword

  Try:Search for messages about 'project update'Try:Find messages where we discussed the budget
• send_message

  Send a message to a LinkedIn user (requires confirmation)

  Try:Send message to John Smith about meeting next weekTry:Reply to Jane Doe's message with my updated resume
• get_company_profile

  Extract company information with explicit section selection (posts, jobs); about-section references may include a company_urn entry carrying the numeric id used by LinkedIn's people-search currentCompany URL facet

  Try:Get information about Microsoft's company profileTry:Show me recent posts from Google's company page
• search_companies

  Search for companies on LinkedIn by keywords

  Try:Find companies in the tech industry in San FranciscoTry:Search for 'data analytics' companies with 1000+ employees
• search_jobs

  Search for jobs with keywords and location filters

  Try:Find software engineering jobs in New YorkTry:Search for remote marketing positions at startups
• search_people

  Search for people by keywords, location, connection degree (1st/2nd/3rd), and current company

  Try:Find software engineers in London with 2nd degree connectionTry:Search for product managers at Google in San Francisco

Comparable tools

Installation

{
  "mcpServers": {
    "linkedin": {
      "command": "uvx",
      "args": ["linkedin-scraper-mcp@latest"],
      "env": { "UV_HTTP_TIMEOUT": "300" }
    }
  }
}

FAQ

Is this safe to use? Will I get banned?

This tool controls a real browser session; it doesn't exploit undocumented APIs. While LinkedIn's TOS prohibit automated tools, normal usage (not bulk scraping!) hasn't resulted in bans for users so far.

What if my agents execute too many actions?

LinkedIn may send warnings about automated tool usage. If that happens, reduce your automation volume. This MCP executes tool calls sequentially via a queue but has no built-in rate limits.

On Hacker News

Recent discussion from the developer community.

• LinkedIn MCP Server▲ 3
  Story by wslh · 2026-04-01
• Open-source MCP server for LinkedIn▲ 2
  Story by arguflow · 2026-04-11

Compare linkedin-mcp-server with