LinkedIn MCP Server: Linked API MCP for Claude, ChatGPT, Cursor and Codex
Linked API MCP server connects your LinkedIn account to AI assistants like Claude, Claude Code, ChatGPT, Codex, Cursor, VS Code, Windsurf, and more. Ask them to search for leads, send messages, analyze profiles, and much more – they'll handle it through our cloud browser, safely and automatically.
Source code available on GitHub.
Does LinkedIn have an official MCP server?
Only a narrow one. LinkedIn's own MCP server, LinkedIn Hiring Pro, is listed in Claude's connector directory since October 2026 and drafts and posts one free job for eligible members – it does not read profiles, run searches or send messages. Beyond that, LinkedIn's developer platform offers REST APIs, most of them gated behind partner approval. Linked API MCP is an unofficial LinkedIn MCP server: it runs LinkedIn actions through a dedicated cloud browser on an account you own, so your assistant searches, reads and messages the way you would, at a human pace, and Linked API never stores your password. Install it in Claude, Claude Code, ChatGPT, Codex, Cursor, VS Code or Windsurf and ask in plain language.
How do I connect Claude to LinkedIn?
Add Linked API to Claude as a custom connector. One connector covers claude.ai, the Claude Desktop app and Cowork. On individual plans, add it under Customize → Connectors with your Linked API server URL; on Team and Enterprise plans, an Owner adds it once in the organization settings. Claude can then search people and companies, read profiles and posts, and send messages from your own account (step-by-step). Claude Code connects through the same MCP server, the CLI or the LinkedIn skill. LinkedIn's own Hiring Pro connector, above, covers job posting only.
Common use cases
- Sales automation assistant. Ask your AI to find leads, check their profiles, and draft personalized outreach. It can search for "software engineers at companies with 50-200 employees in San Francisco", analyze their backgrounds, and suggest connection messages that actually make sense.
- Recruitment assistant. Let your assistant search for candidates with specific skills, review their experience, and send initial outreach. It handles the time-consuming parts while you focus on actually talking to people.
- Conversation assistant. Your AI can read your existing LinkedIn conversations and help you respond naturally. It understands the context of your chats, suggests relevant replies, and can even send follow-up messages.
- Market research assistant. Need competitor analysis? Your assistant can gather data about companies, their employees, and recent activities. Get insights about industry trends without spending hours on LinkedIn.
Which LinkedIn MCP server fits?
The LinkedIn MCP servers people compare connect in four different ways, and the connection decides what your assistant can do:
| Type | Examples | Connects through | What the assistant can do | Whose account |
|---|---|---|---|---|
| Official-API servers | Zapier MCP, Composio, Postiv | OAuth to LinkedIn's official API | Publish posts and, depending on the server, schedule or comment, read your own posts and analytics, look up a member by ID or a company you manage – no messaging, connection requests or people search advertised | Yours |
| Open-source session servers | stickerdaniel/linkedin-mcp-server | Your LinkedIn browser session, run on your own machine | Read profiles, companies, jobs, the feed and the inbox; search people and posts; send messages and connection requests – no posting | Yours, on your machine |
| Public-data extraction | Apify, Bright Data | The vendor's scraping infrastructure, no LinkedIn sign-in | Extract public data; coverage depends on the scraper – Apify's LinkedIn MCP page documents profiles and company information, Bright Data's lists profiles, companies, jobs, posts and people search. No LinkedIn messaging, posting or connection tools advertised | None |
| Account API in a cloud browser | Linked API | A dedicated cloud browser on your account | Search people, companies, posts and jobs; read profiles, the feed and the inbox; message, connect, post, comment and react; Sales Navigator | Yours |
- Only want to publish? An official-API posting server is the narrower fit – it works through LinkedIn's own API.
- Need bulk public data and no actions? A scraper returns it without a LinkedIn account.
- Want an assistant that researches and acts in your account from Claude, ChatGPT, Cursor or Codex, with nothing to run locally? That is what Linked API is for – see the available tools.
Facts checked October 29, 2026 against each server's own page.
How to get started
To start using Linked API MCP, spend 2 minutes reading these essential guides:
- Installation – set up the LinkedIn MCP server in Claude, Claude Desktop, Claude Code, ChatGPT, Codex, Cursor, VS Code or Windsurf.
- Available tools – explore all the LinkedIn tools your assistant can call.
- Usage examples – see real-world examples to get you started quickly.