LinkedIn MCP Server

📖 Overview

LinkedIn MCP Server is a Model Context Protocol (MCP) implementation that bridges language models and other applications with LinkedIn's API. It provides a standardized interface for executing LinkedIn operations through various tools defined by the MCP standard.

🚀 Features

This server provides the following capabilities through MCP tools:

Tool	Description
`get_profile_info`	Retrieve LinkedIn profile information (current user or specified person)
`create_text_post`	Create a text post on LinkedIn with customizable visibility
`create_article_post`	Create an article post with title and content
`get_user_posts`	Retrieve recent posts from a user's profile
`get_network_updates`	Get network updates from LinkedIn feed
`search_people`	Search for people on LinkedIn
`get_company_info`	Retrieve information about a LinkedIn company

🔧 Prerequisites

You'll need one of the following:

Docker: Docker installed and running (recommended)
Python: Python 3.12+ with pip

⚙️ Setup & Configuration

LinkedIn App Setup

Create a LinkedIn App:
- Visit the LinkedIn Developer Portal
- Create a new application and add it to your developer account
- Under the "Auth" section, configure the following scopes:
  - r_liteprofile (for basic profile access)
  - w_member_social (for posting content)
- Copy your Client ID and Client Secret
Generate Access Token:
- Use LinkedIn's OAuth2 authorization code flow
- Navigate to OAuth2 > URL Generator in the LinkedIn Developer Portal
- Generate an access token with the required scopes
- For testing, you can use the temporary access token provided in the developer console
Environment Configuration
Create your environment file:
cp .env.example .env
Edit the .env file with your LinkedIn credentials:
LINKEDIN_ACCESS_TOKEN=YOUR_ACTUAL_LINKEDIN_ACCESS_TOKEN LINKEDIN_MCP_SERVER_PORT=5000
🏃‍♂️ Running the Server

Option 1: Docker (Recommended)

The Docker build must be run from the project root directory (klavis/):

# Navigate to the root directory of the project
cd /path/to/klavis

# Build the Docker image
docker build -t linkedin-mcp-server -f mcp_servers/linkedin/Dockerfile .

# Run the container
docker run -d -p 5000:5000 --name linkedin-mcp linkedin-mcp-server

To use your local .env file instead of building it into the image:

docker run -d -p 5000:5000 --env-file mcp_servers/linkedin/.env --name linkedin-mcp linkedin-mcp-server

Option 2: Python Virtual Environment

# Navigate to the LinkedIn server directory
cd mcp_servers/linkedin

# Create and activate virtual environment
python -m venv venv
source venv/bin/activate  # On Windows: venv\Scripts\activate

# Install dependencies
pip install -r requirements.txt

# Run the server
python server.py

Once running, the server will be accessible at http://localhost:5000.

🔌 API Usage

The server implements the Model Context Protocol (MCP) standard. Here's an example of how to call a tool:

import httpx

async def call_linkedin_tool():
    url = "http://localhost:5000/mcp"
    payload = {
        "tool_name": "linkedin_create_text_post",
        "tool_args": {
            "text": "Hello from LinkedIn MCP Server!",
            "visibility": "PUBLIC"
        }
    }
    
    async with httpx.AsyncClient() as client:
        response = await client.post(url, json=payload)
        result = response.json()
        return result

📋 Common Operations

Getting Profile Information

payload = {
    "tool_name": "linkedin_get_profile_info",
    "tool_args": {}  # Empty for current user, or provide person_id
}

Creating a Text Post

payload = {
    "tool_name": "linkedin_create_text_post",
    "tool_args": {
        "text": "Excited to share my latest project!",
        "visibility": "PUBLIC"
    }
}

Creating an Article Post

payload = {
    "tool_name": "linkedin_create_article_post",
    "tool_args": {
        "title": "The Future of AI",
        "text": "In this article, I explore the latest trends in artificial intelligence...",
        "visibility": "PUBLIC"
    }
}

Searching for People

payload = {
    "tool_name": "linkedin_search_people",
    "tool_args": {
        "keywords": "software engineer",
        "count": 10
    }
}

🛠️ Troubleshooting

Docker Build Issues

File Not Found Errors: If you see errors like failed to compute cache key: failed to calculate checksum of ref: not found, this means Docker can't find the files referenced in the Dockerfile. Make sure you're building from the root project directory (klavis/), not from the server directory.

Common Runtime Issues

Authentication Failures: Verify your access token is correct and hasn't expired. LinkedIn access tokens typically have a short lifespan.
API Errors: Check LinkedIn API documentation for error meanings and status codes.
Missing Permissions: Ensure your LinkedIn app has the necessary scopes enabled (r_liteprofile, w_member_social).
Rate Limiting: LinkedIn has strict rate limits. Implement appropriate delays between requests if needed.
Scope Issues: Some endpoints require additional permissions or LinkedIn partnership status.

🤝 Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

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

📜 License

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

This server cannot be installed

security - not tested

license - not found

quality - not tested

How are these scores calculated?

A Model Context Protocol implementation that bridges language models with LinkedIn's API, enabling profile access, posting content, searching people, and retrieving company information through standardized tools.

Related MCP Servers

LinkedIn MCP Server
Hritik003
-
security
F
license
-
quality
A Model Context Protocol server that enables seamless interaction with LinkedIn for job applications, profile retrieval, feed browsing, and resume analysis through natural language commands.
Last updated -
19
Python
EnrichB2B MCP Server
moonlabsai
-
security
F
license
-
quality
A server implementing the Model Context Protocol that enables users to retrieve LinkedIn profile information and activity data via EnrichB2B API, and generate text using OpenAI GPT-4 or Anthropic Claude models.
Last updated -
1
Python
LinkedIn MCP Server
felipfr
A
security
A
license
A
quality
Enables AI assistants to interact with LinkedIn data through the Model Context Protocol, allowing profile searches, job discovery, messaging, and network analytics.
Last updated -
28
6
11
TypeScript
MIT License
Linkd MCP Server
automcp-app
A
security
F
license
A
quality
An unofficial Model Context Protocol server that enables programmatic access to LinkedIn data through tools like user search, company search, profile enrichment, and contact retrieval.
Last updated -
7
419
2
TypeScript

View all related MCP servers

Appeared in Searches

Finding people named Altman on LinkedIn

LinkedIn MCP Server