LinkedIn API MCP server for AI agents

The HDW MCP Server provides comprehensive access to LinkedIn data and functionalities through the HorizonDataWave API, enabling you to search for users, retrieve profiles, manage connections, and interact with LinkedIn content through a Model Context Protocol interface.

Installation

Using Smithery (Recommended)

Install HDW MCP Server automatically for Claude Desktop:

npx -y @smithery/cli install @horizondatawave/hdw-mcp-server --client claude

Manual Installation

Step 1: Clone the Repository

# Clone the repository
git clone https://github.com/horizondatawave/hdw-mcp-server.git

# Change directory to the project folder
cd hdw-mcp-server

# Install dependencies
npm install

Step 2: Get API Credentials

HDW_ACCESS_TOKEN
HDW_ACCOUNT_ID

Step 3: Configure Environment

Create a .env file in the project root with your credentials:

HDW_ACCESS_TOKEN=YOUR_HD_W_ACCESS_TOKEN
HDW_ACCOUNT_ID=YOUR_HD_W_ACCOUNT_ID

Client Setup

Claude Desktop

Update your Claude configuration file with:

{
  "mcpServers": {
    "hdw": {
      "command": "npx",
      "args": ["-y","@horizondatawave/mcp"],
      "env": {
        "HDW_ACCESS_TOKEN": "YOUR_HD_W_ACCESS_TOKEN",
        "HDW_ACCOUNT_ID": "YOUR_HD_W_ACCOUNT_ID"
      }
    }
  }
}

Configuration file location:

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

Cursor

Option 1 (Simple):
In Cursor Settings, add a new MCP server with the command:

env HDW_ACCESS_TOKEN=your-access-token HDW_ACCOUNT_ID=your-account-id node /path/to/your/build/index.js

Option 2 (Recommended):
Copy run.template.sh to a new file (e.g., run.sh), update it with your credentials, and configure Cursor to run:

sh /path/to/your/run.sh

Windsurf

Update your Windsurf configuration file (mcp_config.json):

{
  "mcpServers": {
    "hdw": {
      "command": "node",
      "args": ["/path/to/your/build/index.js"],
      "env": {
        "HDW_ACCESS_TOKEN": "YOUR_HD_W_ACCESS_TOKEN",
        "HDW_ACCOUNT_ID": "YOUR_HD_W_ACCOUNT_ID"
      }
    }
  }
}

Note: Consider disabling official web tools to conserve API credits.

Available Tools

LinkedIn User Search and Profiles

Search LinkedIn Users

Find LinkedIn users with various filters:

Keywords, name, title, company, location, industry, education
Configurable result count and timeout

{
  "name": "search_linkedin_users",
  "parameters": {
    "keywords": "software engineer",
    "company_keywords": "Google",
    "count": 20
  }
}

Get LinkedIn Profile

Retrieve detailed profile information:

{
  "name": "get_linkedin_profile",
  "parameters": {
    "user": "https://www.linkedin.com/in/username/"
  }
}

Email Lookup

Look up LinkedIn users by email:

{
  "name": "get_linkedin_email_user",
  "parameters": {
    "email": "[email protected]"
  }
}

Posts and Interactions

Get LinkedIn User Posts

Retrieve posts for a LinkedIn user:

{
  "name": "get_linkedin_user_posts",
  "parameters": {
    "urn": "fsd_profile:AAE12345678",
    "count": 15
  }
}

Get LinkedIn Post Comments

Retrieve comments for a specific post:

{
  "name": "get_linkedin_post_comments",
  "parameters": {
    "urn": "activity:6789012345678",
    "sort": "recent",
    "count": 25
  }
}

Get LinkedIn Post Reposts

Retrieve reposts for a LinkedIn post:

{
  "name": "get_linkedin_post_reposts",
  "parameters": {
    "urn": "activity:6789012345678"
  }
}

Account Management

Send LinkedIn Chat Message

Send a chat message using the LinkedIn management API:

{
  "name": "send_linkedin_chat_message",
  "parameters": {
    "user": "fsd_profile:AAE12345678",
    "text": "Hello, I'd like to connect!"
  }
}

Send LinkedIn Connection Request

Send a connection invitation:

{
  "name": "send_linkedin_connection",
  "parameters": {
    "user": "fsd_profile:AAE12345678"
  }
}

Get LinkedIn User Connections

Retrieve a list of LinkedIn user connections:

{
  "name": "get_linkedin_user_connections",
  "parameters": {
    "count": 50
  }
}

Company Data

Find LinkedIn Companies via Google

Find LinkedIn companies using Google search:

{
  "name": "get_linkedin_google_company",
  "parameters": {
    "keywords": ["Acme Corporation"],
    "with_urn": true
  }
}

Get LinkedIn Company Details

Retrieve detailed information about a LinkedIn company:

{
  "name": "get_linkedin_company",
  "parameters": {
    "company": "https://www.linkedin.com/company/google/"
  }
}

Get LinkedIn Company Employees

Retrieve employees for a given LinkedIn company:

{
  "name": "get_linkedin_company_employees",
  "parameters": {
    "companies": ["urn:li:fs_miniCompany:1441"],
    "count": 20
  }
}

How to add this MCP server to Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.