OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
MCP & Tooling

Linkedin MCP Server

Linkedin MCP Server is a self-hosted Python MCP server that connects an MCP-compatible AI client to LinkedIn through a user's browser session. It exposes tools for reading profiles, researching companies, finding jobs, and managing conversations and connection requests.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Linkedin MCP Server — OpenViST project profile in MCP & Tooling.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it when you want an MCP-compatible AI client to access LinkedIn tasks through a browser session and are prepared to configure and run the server.

Who it is for

  • Developers configuring an MCP server for an AI client.
  • AI assistant users who want LinkedIn profile, company or job research in an MCP workflow.
  • Users who want an AI client to assist with LinkedIn conversations and connection requests.

Documented uses

  • Read profile sections such as experience, education, skills, projects and posts.
  • Research company information and find LinkedIn job listings.
  • Manage conversations and connection requests through an AI-agent workflow.
Before you choose

Requirements & limits

The project is open source under Apache-2.0. Its README documents local uvx installation and browser-session authentication.

  • Requires an MCP-compatible client and a local or self-hosted server setup.
  • The documented uvx path requires uv and an MCP client's mcpServers configuration.
  • The server uses a signed-in local browser session when available and otherwise opens a LinkedIn login browser.
  • The README lists stdio as the default transport and Streamable HTTP as another mode.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Set up the server with uvx

Add the LinkedIn MCP server to an MCP client's configuration and prepare its browser-session authentication.

Before you start

  • uv installed
  • An MCP-compatible client with an mcpServers configuration

Steps

  1. Add the documented mcp-server-linkedin entry using command uvx and argument mcp-server-linkedin@latest to the client's mcpServers configuration.

  2. Start the server through the MCP client; it prepares its shared Patchright Chromium browser cache.

  3. On the first tool call requiring authentication, allow it to reuse a signed-in local browser session or open a LinkedIn login window. Alternatively, run uvx mcp-server-linkedin@latest --login to create a session explicitly.

Expected outcome

The MCP client is configured to start the server, and a LinkedIn browser session can be used for authenticated tools.

Guide limitations

  • Early tool calls may report setup or authentication in progress until browser setup or login finishes.
  • The @latest tag enables automatic updates; the README advises AI agents to get user confirmation before enabling them.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
9 October 2026
Original website title
stickerdaniel/linkedin-mcp-server · Official homepage title · retained in its source language
How we review sourcesSuggest a correction