LinkedIn MCP Server

Empower your AI agents with professional networking capabilities.

A Model Context Protocol (MCP) server that enables Large Language Models (LLMs) like Claude to interact with LinkedIn's professional network. Built with FastMCP for high performance and reliability.

Features

• 🔐 Secure OAuth 2.0 Authentication - Complete OAuth flow implementation
• 📝 Content Management - Create, update, and delete posts with text and images
• 💬 Engagement Tools - Comment on posts and manage interactions
• 👥 Profile Access - Retrieve your profile and member information
• 🏢 Company Intelligence - Search companies and access organization data
• 💼 Job Search - Find and explore job opportunities
• 🔍 People Search - Discover professionals across LinkedIn

Installation

Using uvx (Recommended)

The easiest way to use the LinkedIn MCP server is with uvx:

uvx linkedin-mcp-server

Using pip

pip install linkedin-mcp-server

From Source

git clone https://github.com/SARAMALI15792/LinkedIn_mcp_custom_server.git
cd LinkedIn_mcp_custom_server
pip install -e .

Quick Start

1. Setup LinkedIn App Credentials

1. Visit LinkedIn Developer Portal
2. Create a new app
3. Request access to:
   • "Sign In with LinkedIn using OpenID Connect"
   • "Share on LinkedIn"
4. Add redirect URL: http://localhost:8000
5. Note your Client ID and Client Secret

2. Configure Environment

Create a .env file in your working directory:

LINKEDIN_CLIENT_ID=your_client_id
LINKEDIN_CLIENT_SECRET=your_client_secret
LINKEDIN_REDIRECT_URI=http://localhost:8000

3. Configure Claude Desktop

Add to your Claude Desktop config file:

Windows: %APPDATA%\Claude\claude_desktop_config.json macOS: ~/Library/Application Support/Claude/claude_desktop_config.json Linux: ~/.config/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "linkedin": {
      "command": "uvx",
      "args": ["linkedin-mcp-server"]
    }
  }
}

Alternative with pip installation:

{
  "mcpServers": {
    "linkedin": {
      "command": "linkedin-mcp-server"
    }
  }
}

4. Authenticate

1. In Claude Desktop, ask: "Generate LinkedIn login URL"
2. Open the provided URL in your browser
3. Authorize the application
4. Copy the code parameter from the redirect URL
5. In Claude: "Exchange this code: [PASTE_CODE]"

You're now connected!

Usage Examples

Once authenticated, you can use natural language to interact with LinkedIn:

Creating Content

"Create a LinkedIn post: 'Excited to share my new MCP server project! 🚀 #AI #LinkedIn'"

"Post this image with caption 'Team photo from the conference': C:/photos/team.jpg"

Engagement

"Show me comments on my latest post"

"Comment on post urn:li:share:123456789: 'Great insights, thanks for sharing!'"

Profile & Network

"What's my LinkedIn email address?"

"Search for Python developers in San Francisco"

"Get details for company urn:li:organization:1234567"

Job Search

"Find remote Senior Python Developer positions"

"Search for Machine Learning jobs in New York"

"Get details for job urn:li:job:123456789"

Available Tools

Tool	Description
linkedin_get_oauth_url	Generate OAuth 2.0 authorization URL
linkedin_exchange_code	Exchange auth code for access token
linkedin_get_my_profile	Get authenticated user's profile
linkedin_get_member_profile	Get member profile by URN
linkedin_create_post	Create text post
linkedin_create_image_post	Create post with image
linkedin_update_post	Update existing post (recreates)
linkedin_delete_post	Delete post
linkedin_get_recent_posts	List recent posts (restricted)
linkedin_create_comment	Comment on content
linkedin_get_post_comments	Get comments on post
linkedin_delete_comment	Delete comment
linkedin_get_company_profile	Get company details
linkedin_search_companies	Search for companies
linkedin_search_jobs	Search job postings
linkedin_get_job_details	Get job details
linkedin_search_people	Search for people

Architecture

linkedin-mcp-server/
├── linkedin_mcp_server/
│   ├── __init__.py          # Package initialization
│   ├── __main__.py          # CLI entry point
│   ├── server.py            # Main MCP server with tool definitions
│   ├── config.py            # Configuration management
│   ├── utils.py             # Shared utilities
│   └── tools/               # Tool implementations
│       ├── auth.py          # OAuth 2.0 flow
│       ├── profile.py       # Profile operations
│       ├── post.py          # Post & comment operations
│       ├── company.py       # Company operations
│       ├── job.py           # Job search operations
│       └── search.py        # People search
├── pyproject.toml           # Package metadata
├── README.md                # This file
└── LICENSE                  # MIT License

API Permissions & Limitations

Granted Permissions

• ✅ openid, profile, email - Basic profile access
• ✅ w_member_social - Create posts and comments

Restricted Permissions

Many LinkedIn API endpoints require additional permissions that are restricted:

• ⚠️ r_member_social - Read user's posts (often unavailable)
• ⚠️ People/Company search - May require Marketing API access
• ⚠️ Job search - May require Talent Solutions access

These limitations are imposed by LinkedIn, not this MCP server.

Development

Setup Development Environment

git clone https://github.com/SARAMALI15792/LinkedIn_mcp_custom_server.git
cd LinkedIn_mcp_custom_server
pip install -e ".[dev]"

Run Tests

pytest tests/

Code Quality

# Format code
black linkedin_mcp_server/

# Lint
ruff check linkedin_mcp_server/

# Type check
mypy linkedin_mcp_server/

Troubleshooting

Authentication Issues

Problem: "Unauthorized (401)" errors Solution: Your access token may have expired. Re-authenticate using the OAuth flow.

Problem: "Forbidden (403)" errors Solution: Your app lacks required permissions. Check your LinkedIn app settings.

Connection Issues

Problem: Server not starting Solution:

1. Check .env file exists with correct credentials
2. Verify LINKEDIN_CLIENT_ID and LINKEDIN_CLIENT_SECRET are set
3. Check Claude Desktop config is correct

Permission Errors

Problem: "r_member_social permission required" Solution: This permission is restricted by LinkedIn. Most third-party apps cannot access these endpoints.

Security Best Practices

• ✅ Never commit .env files with credentials
• ✅ Use environment variables for sensitive data
• ✅ Regularly rotate access tokens
• ✅ Only request minimum required permissions
• ✅ Use HTTPS for redirect URIs in production

Contributing

Contributions are welcome! Please:

1. Fork the repository
2. Create a feature branch (git checkout -b feature/amazing-feature)
3. Commit your changes (git commit -m 'Add amazing feature')
4. Push to the branch (git push origin feature/amazing-feature)
5. Open a Pull Request

License

This project is licensed under the MIT License - see the LICENSE file for details.

Support

• 🐛 Report bugs: GitHub Issues
• 📖 Documentation: GitHub README
• 💬 Questions: Open a GitHub Discussion

Credits

Built with:

• FastMCP - Fast MCP server framework
• Model Context Protocol - Protocol for LLM integrations
• LinkedIn API - LinkedIn's developer platform

Author

SARAM ALI Email: saramali15792@gmail.com GitHub: @SARAMALI15792

---

Made with ❤️ for the AI and LinkedIn communities