LinkedIn

v1.0.0Communicationstable

A Custom MCP Server for LinkedIn integration built with FastMCP.

linkedin-mcp-custom-servermcpai-integration
Share:
10
Stars
0
Downloads
0
Weekly
0/5

What is LinkedIn?

LinkedIn is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to custom mcp server for linkedin integration built with fastmcp.

A Custom MCP Server for LinkedIn integration built with FastMCP.

This server falls under the Communication category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • A Custom MCP Server for LinkedIn integration built with Fast

Use Cases

Manage LinkedIn interactions through FastMCP integration with AI assistants.
SARAMALI15792

Maintainer

LicenseMIT
Languagepython
Versionv1.0.0
UpdatedMay 8, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

Manual Installation

npx linkedin-mcp-custom-server

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use LinkedIn

The LinkedIn MCP Custom Server is a FastMCP-powered integration that exposes 18 LinkedIn API tools to AI assistants, covering OAuth authentication, profile lookups, post creation and management, commenting, company search, job search, and people search. It handles the full OAuth 2.0 flow so your AI client can interact with LinkedIn on your behalf after a one-time authorization.

Prerequisites

  • Python 3.9 or higher installed
  • A LinkedIn Developer App with OAuth 2.0 credentials (Client ID and Client Secret)
  • LinkedIn App configured with redirect URI http://localhost:8000
  • uvx or pip package manager installed
  • Claude Desktop or another MCP-compatible client
1

Install the LinkedIn MCP server

Install the package using uvx (recommended for isolated execution) or pip. The uvx method runs the server without a permanent installation.

# Recommended: install with pip
pip install linkedin-mcp-server

# Or use uvx for isolated runs
uvx linkedin-mcp-server
2

Create a LinkedIn Developer App

Go to https://developer.linkedin.com and create an app. Note your Client ID and Client Secret, and add http://localhost:8000 as an authorized redirect URI under the OAuth 2.0 settings.

3

Configure environment variables

Create a .env file in your working directory (or set these as environment variables) with your LinkedIn OAuth credentials.

LINKEDIN_CLIENT_ID=your_client_id_here
LINKEDIN_CLIENT_SECRET=your_client_secret_here
LINKEDIN_REDIRECT_URI=http://localhost:8000
4

Add the server to Claude Desktop config

Register the server in your Claude Desktop configuration file at ~/Library/Application Support/Claude/claude_desktop_config.json (macOS).

{
  "mcpServers": {
    "linkedin": {
      "command": "uvx",
      "args": ["linkedin-mcp-server"],
      "env": {
        "LINKEDIN_CLIENT_ID": "your_client_id_here",
        "LINKEDIN_CLIENT_SECRET": "your_client_secret_here",
        "LINKEDIN_REDIRECT_URI": "http://localhost:8000"
      }
    }
  }
}
5

Authorize via OAuth

On first use, ask the AI to generate an OAuth URL, visit it in your browser to authorize the app, then provide the returned code to exchange for an access token.

LinkedIn Examples

Client configuration

Complete claude_desktop_config.json entry for the LinkedIn MCP server using uvx.

{
  "mcpServers": {
    "linkedin": {
      "command": "uvx",
      "args": ["linkedin-mcp-server"],
      "env": {
        "LINKEDIN_CLIENT_ID": "your_client_id_here",
        "LINKEDIN_CLIENT_SECRET": "your_client_secret_here",
        "LINKEDIN_REDIRECT_URI": "http://localhost:8000"
      }
    }
  }
}

Prompts to try

Example natural language prompts to use with the LinkedIn MCP server after OAuth authorization.

- "Generate my LinkedIn login URL so I can authorize the app"
- "Show me my LinkedIn profile information"
- "Post to LinkedIn: Excited to share my latest project on AI-powered developer tools!"
- "Search LinkedIn for companies named Microsoft"
- "Find remote Python developer jobs on LinkedIn"
- "Get the comments on post urn:li:share:7289123456789"

Troubleshooting LinkedIn

OAuth redirect fails or returns an error

Verify that http://localhost:8000 is listed as an authorized redirect URI in your LinkedIn Developer App settings. The redirect URI in your .env must exactly match what is registered in the LinkedIn portal.

Tools return 403 Forbidden errors

LinkedIn API scopes must be explicitly granted on your Developer App. Enable the required product permissions (Share on LinkedIn, Sign In with LinkedIn, etc.) in the LinkedIn Developer portal and re-authorize.

Access token expires and tools stop working

LinkedIn access tokens have a limited lifetime. Use linkedin_get_oauth_url and linkedin_exchange_code again to re-authorize and obtain a fresh token.

Frequently Asked Questions about LinkedIn

What is LinkedIn?

LinkedIn is a Model Context Protocol (MCP) server that custom mcp server for linkedin integration built with fastmcp. It connects AI assistants to external tools and data sources through a standardized interface.

How do I install LinkedIn?

Follow the installation instructions on the LinkedIn GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with LinkedIn?

LinkedIn works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is LinkedIn free to use?

Yes, LinkedIn is open source and available under the MIT license. You can use it freely in both personal and commercial projects.

Browse More Communication MCP Servers

Explore all communication servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Quick Config Preview

{ "mcpServers": { "linkedin-mcp-custom-server": { "command": "npx", "args": ["-y", "linkedin-mcp-custom-server"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use LinkedIn?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides