LinkedIn MCP Server

A powerful Model Context Protocol (MCP) server that enables AI agents like Claude to interact seamlessly with LinkedIn's professional network. Built with FastMCP for high performance and reliability.

What is This?

This MCP server bridges the gap between AI assistants and LinkedIn, allowing them to:

• Create and manage LinkedIn posts with text and images

• Comment on posts and engage with content

• Access profile information

• Search for companies, jobs, and people

• Automate LinkedIn interactions through natural language

Perfect for professionals who want to leverage AI to manage their LinkedIn presence efficiently.

Features

Core Capabilities

• Secure Authentication - OAuth 2.0 flow with access token management

• Content Creation - Publish text posts and image posts

• Content Management - Update and delete posts

• Engagement - Comment on posts and manage comments

• Profile Access - Retrieve authenticated user profile information

• Company Intelligence - Search and view company profiles

• Job Discovery - Search job postings and view details

• People Search - Find professionals on LinkedIn

Built With

• FastMCP - Modern Python MCP framework

• httpx - Async HTTP client for API calls

• Pydantic - Data validation and settings management

• OAuth 2.0 - Industry-standard authentication

Installation

Option 1: Using uvx (Recommended)

The fastest way to get started:

Option 2: Using pip

Install from PyPI:

Option 3: From Source

For development or customization:

Quick Start Guide

Step 1: Create LinkedIn App

1. Go to LinkedIn Developer Portal

2. Click "Create app"

3. Fill in required information:

   • App name: Choose a descriptive name

   • LinkedIn Page: Associate with your page or create one

   • App logo: Upload a logo (optional but recommended)

4. Request access to these products:

   • Sign In with LinkedIn using OpenID Connect (instant approval)

   • Share on LinkedIn (instant approval)

5. In the "Auth" tab:

   • Add Redirect URL: http://localhost:8000

   • Copy your Client ID

   • Copy your Client Secret

Step 2: Configure Environment

Create a .env file in your working directory:

Security Note: Never commit the .env file to version control. It's already in .gitignore.

Step 3: Configure Claude Desktop

Edit your Claude Desktop configuration file:

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

Add the LinkedIn MCP server:

If installed via pip:

For local development:

Step 4: Authenticate with LinkedIn

1. Restart Claude Desktop

2. In Claude, type: "Generate LinkedIn login URL"

3. Copy and open the URL in your browser

4. Sign in to LinkedIn and authorize the application

5. You'll be redirected to http://localhost:8000/?code=...

6. Copy the code parameter value from the URL

7. In Claude, type: "Exchange this code: [paste the code]"

8. Done! You're now authenticated.

Your access token is automatically saved to

Usage Examples

Authentication

Creating Posts

Text Post:

Post with Image:

Managing Content

Update a Post:

Delete a Post:

Engagement

Comment on Posts:

View Comments:

Profile Information

Company Research

Job Search

People Search

Available Tools

Understanding LinkedIn URNs

LinkedIn uses URNs (Uniform Resource Names) to identify resources:

• Person: urn:li:person:AbC123XyZ

• Post/Share: urn:li:share:7289123456789

• Comment: urn:li:comment:(ugcPost:7289123456789,7289987654321)

• Organization: urn:li:organization:1035

• Job: urn:li:job:123456789

When Claude returns a URN, you can use it to reference that resource in other commands.

API Permissions and Limitations

Available Permissions

This server requests these OAuth scopes:

• openid - OpenID Connect authentication

• profile - Access to profile information

• email - Access to email address

• w_member_social - Create posts and comments

Known Limitations

Some LinkedIn API features require additional permissions that are restricted to approved partners:

Restricted Read Operations:

• r_member_social - Read user's posts (rarely granted to third-party apps)

• Marketing Developer Platform - Advanced company/people search

• Talent Solutions - Advanced job search features

What This Means:

• Creating posts: Works perfectly

• Deleting posts: Works perfectly

• Reading your own posts: May not work (requires restricted permission)

• Advanced search: May require approval for Marketing/Talent APIs

Why? LinkedIn restricts these APIs to protect user privacy and control third-party access to their platform.

Project Structure

Development

Setting Up Development Environment

Running Tests

Code Quality

Running Locally

Troubleshooting

Authentication Issues

Problem: "Error: LINKEDIN_CLIENT_ID not configured" Solution: Create .env file with your LinkedIn app credentials

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

Problem: "Error exchanging code: invalid code" Solution: Authorization codes expire quickly. Generate a new OAuth URL and try again

API Errors

Problem: "Forbidden (403)" errors Solution: Your LinkedIn app may lack required permissions. Check your app's products in the Developer Portal

Problem: "r_member_social permission required" Solution: This permission is restricted. LinkedIn rarely grants it to third-party apps. Focus on write operations instead

Problem: Can't search companies/jobs/people Solution: These APIs may require Marketing/Talent Solutions products which need LinkedIn approval

Connection Issues

Problem: MCP server not connecting in Claude Desktop Solution:

1. Verify claude_desktop_config.json syntax is valid JSON

2. Check that the command path is correct

3. Restart Claude Desktop

4. Check Claude Desktop logs for error messages

Problem: ".env file not found" Solution: Create .env file in the same directory where Claude Desktop runs the server, or specify environment variables in the config

Security Best Practices

1. Never commit credentials - .env is in .gitignore for a reason

2. Rotate tokens regularly - Re-authenticate periodically for security

3. Use HTTPS in production - Update redirect URI to HTTPS for production apps

4. Minimum permissions - Only request scopes you actually need

5. Review app access - Regularly check LinkedIn's "Apps" section in settings

Contributing

Contributions are welcome! Here's how:

1. Fork the repository

2. Create a feature branch: git checkout -b feature/amazing-feature

3. Make your changes

4. Run tests: pytest tests/

5. Format code: black linkedin_mcp_server/

6. Commit: git commit -m 'Add amazing feature'

7. Push: git push origin feature/amazing-feature

8. Open a Pull Request

Contribution Guidelines

• Follow existing code style (Black formatter, 100 char line length)

• Add tests for new features

• Update documentation as needed

• Keep commits focused and atomic

• Write clear commit messages

Roadmap

Future enhancements being considered:

• Token refresh flow implementation

• Webhook support for real-time notifications

• Enhanced error handling and retry logic

• Pagination support for search results

• Bulk operations for efficiency

• Analytics and insights (if API access granted)

• Connection management features

• Message sending (if Messaging API access granted)

FAQ

Q: Why can't I read my own posts? A: The r_member_social permission required to read posts is restricted by LinkedIn. Most third-party apps cannot access this feature.

Q: How long do to access tokens last? A: LinkedIn controls token expiration. Typically tokens last for 60 days, but this can vary. You'll need to re-authenticate when tokens expire.

Q: Can I use this for multiple LinkedIn accounts? A: Currently, the server is designed for single-user authentication. Each .env file holds one access token.

Q: Is this officially supported by LinkedIn? A: No, this is a community project. It uses LinkedIn's public APIs but is not officially endorsed by LinkedIn.

Q: Can I use this commercially? A: Yes, the MIT license allows commercial use. However, check LinkedIn's terms of service and API usage policies.

Q: Why do some searches return empty results? A: Search APIs may require additional LinkedIn products (Marketing/Talent) that need approval. Also, API access varies by account type.

Support

• Report bugs: GitHub Issues

• Documentation: GitHub README

• Integration Guide: claude.md

• Discussions: GitHub Discussions

Resources

• FastMCP Documentation

• Model Context Protocol Spec

• LinkedIn API Documentation

• OAuth 2.0 Specification

License

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

Acknowledgments

Built with:

• FastMCP - For the excellent MCP framework

• Model Context Protocol - For enabling AI-agent integrations

• LinkedIn API - For providing professional networking capabilities

• Claude - For inspiring and testing this integration

Author

SARAM ALI

• Email: saramali15792@gmail.com

• GitHub: @SARAMALI15792

• Project: LinkedIn MCP Custom Server

Built with care for the AI and LinkedIn communities | Report Issues | Contribute | Star on GitHub