home / mcp / linkedin posts hunter mcp server

LinkedIn Posts Hunter MCP Server

LinkedIn Posts Hunter MCP is a Model Context Protocol (MCP) server that provides tools for automating LinkedIn job post search and management through your AI assistant (Claude Desktop, Cursor, or other MCP-compatible clients).

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "kevin-weitgenant-linkedin-posts-hunter-mcp-server": {
      "command": "linkedin-posts-hunter-mcp",
      "args": []
    }
  }
}

LinkedIn Posts Hunter MCP Server automates searching and tracking LinkedIn job posts through your AI assistant. It uses a Playwright-based tool for browser automation, stores results locally in a SQLite database, and provides a React dashboard for easy viewing and management. You gain early access to job opportunities found in LinkedIn posts, while keeping all data on your computer for privacy and security.

How to use

You interact with the LinkedIn Posts Hunter MCP Server primarily through your MCP client (Cursor IDE or Claude Desktop) and the built-in React dashboard. Start by authenticating to LinkedIn, then search for posts using keywords, view and filter results, and mark posts as saved or applied. Changes you make in the dashboard are written to a local database, and you can also control the dashboard and data with natural-language commands via your MCP client.

Typical workflow you can achieve: - Authenticate with LinkedIn to establish a persistent session on your computer - Run searches for specific job topics and save results to the local database - Open the React dashboard to visually browse posts, sort by date or engagement, and filter by keywords - Mark posts as applied or saved for later, then use filters to narrow down your view - Use MCP commands to programmatically filter, view, or modify your data and UI state, with updates reflected in real time in the dashboard.

How to install

Prerequisites you need before installation

- Node.js 18 or higher
- npm (comes with Node.js)
- A LinkedIn account
- An MCP client such as Cursor IDE or Claude Desktop

Option A: Method 1 – Using mcp.json Configuration (Recommended) ⭐

1. Install the MCP server globally
```
npm install -g linkedin-posts-hunter-mcp

2. Add to your MCP configuration for Cursor IDE
```
{
  "mcpServers": {
    "linkedin_post_hunter_mcp": {
      "command": "linkedin-posts-hunter-mcp"
    }
  }
}

3. Add to Claude Desktop configuration
```
{
  "mcpServers": {
    "linkedin_post_hunter_mcp": {
      "command": "linkedin-posts-hunter-mcp"
    }
  }
}

4. Restart your MCP client to load the new server.

Option B: Method 2 – Local Development Setup (for contributors)

1. Clone the repository and install dependencies
```
git clone https://github.com/kevin-weitgenant/LinkedIn-Posts-Hunter-MCP-Server.git
cd LinkedIn-Posts-Hunter-MCP-Server
npm run install:all
npm run build

2. Add to your MCP configuration for Cursor IDE
```
{
  "mcpServers": {
    "linkedin_post_hunter_mcp": {
      "command": "node",
      "args": [
        "/absolute/path/to/LinkedIn-Posts-Hunter-MCP-Server/build/index.js"
      ],
      "cwd": "/absolute/path/to/LinkedIn-Posts-Hunter-MCP-Server"
    }
  }
}

3. Add to Claude Desktop configuration
```
{
  "mcpServers": {
    "linkedin_post_hunter_mcp": {
      "command": "node",
      "args": [
        "/absolute/path/to/LinkedIn-Posts-Hunter-MCP-Server/build/index.js"
      ],
      "cwd": "/absolute/path/to/LinkedIn-Posts-Hunter-MCP-Server"
    }
  }
}

4. Restart your MCP client to load the server.

Additional notes

The server stores all scraped data locally in an SQLite database and keeps LinkedIn session cookies in local files. The React dashboard renders posts from the local database and supports filtering, sorting, and quick actions. You can control the dashboard via the UI or through MCP tools like auth, search_posts, manage_posts, viewer_filters, start_viewer, and stop_viewer. All changes stay on your machine, ensuring privacy.

All data is stored in per-user directories on your system. You can remove everything by deleting the data directory if you want to reset the setup.

Security and privacy

All data stays on your computer. No data is sent to external servers unless you explicitly perform actions that require remote resources. Session cookies and authentication tokens are stored locally and referenced by the local browser automation process.

Available tools

auth

Manage LinkedIn authentication with persistent session storage via a browser-based login flow.

search_posts

Search LinkedIn posts by keywords and save results to the local SQLite database.

manage_posts

Read, update, or delete posts from the local database with advanced filtering.

viewer_filters

Control the React UI filters programmatically from the AI conversation.

start_viewer

Launch the React dashboard in your browser to visualize scraped posts.

stop_viewer

Stop the running Vite development server for the dashboard.