home / mcp / linkedin jobs mcp server

LinkedIn Jobs MCP Server

Provides MCP clients access to LinkedIn public job listings with advanced search and filtering.

Installation

Add the following to your MCP client configuration file.

Configuration

{
  "mcpServers": {
    "administrativetrick-linkedin-mcp": {
      "command": "node",
      "args": [
        "/ABSOLUTE/PATH/TO/linkedin-mcp-server/build/index.js"
      ]
    }
  }
}

You can search LinkedIn job listings directly from any MCP client using this server. It enables Claude and other MCP-enabled tools to perform advanced job searches with smart filtering, delivering readable results quickly and without requiring authentication.

How to use

After configuring an MCP client to talk to this server, you can ask for LinkedIn job searches using natural phrases. The server exposes a single tool you can call to search jobs with filters such as location, job type, salary, and experience level. The responses include job titles, companies, locations, posting dates, and application links.

Two local runtime options are provided. You can run the server as a local stdio process or invoke it via npx after publishing. Use the stdio approach if you want a direct node invocation, or use npx for quick testing or deployment in environments with npm access.

To connect Claude Desktop or another MCP client, configure the client with one of the following stdio configurations. Each configuration starts the MCP server locally and communicates over standard input/output.

{
  "mcpServers": {
    "linkedin_jobs": {
      "command": "node",
      "args": [
        "/ABSOLUTE/PATH/TO/linkedin-mcp-server/build/index.js"
      ]
    }
  }
}

How to install

Follow these steps to prepare and run the server locally.

Prerequisites: Install Node.js 18 or higher and a package manager such as npm or yarn.

1. Open a terminal in your project directory where you want to run the MCP server.

2. Install dependencies.

npm install

3. Build the server.

npm run build

Additional usage option

If you prefer to run the server via an npm package after publishing, you can load it with npx. This is convenient for quick experiments or environments where you want to avoid a local build step.

{
  "mcpServers": {
    "linkedin_jobs_npx": {
      "command": "npx",
      "args": [
        "-y",
        "linkedin-jobs-mcp-server"
      ]
    }
  }
}

Configuration and usage notes

The server exposes a single tool you call from your MCP client to perform a LinkedIn job search with filters like location, date posted, salary, and experience level. The client receives a list of matching job postings with essential details and links to apply.

Environment variables are not required for basic operation. If you adapt or extend the server, you can introduce environment variables for secrets or endpoints, but the provided setup works without authentication.

Troubleshooting

If the server does not appear in your MCP client, ensure the path to the built index is absolute and that you restarted the client after configuring.

If you encounter no results, broaden your search terms or adjust filters. Verify that the LinkedIn public listings for your criteria are available.

Build or start errors can often be resolved by reinstalling dependencies and rebuilding.

Available tools

search_linkedin_jobs

Search LinkedIn jobs with advanced filtering options such as keyword, location, date posted, job type, remote status, salary, and experience level. Returns a list of matching job postings with key details and application links.