# Lakome LinkedIn MCP Server

[![Smithery](https://smithery.ai/badge/lakome-linkedin-mcp)](https://smithery.ai/server/lakome-linkedin-mcp)

A lightweight Model Context Protocol (MCP) server providing AI agents with real-time LinkedIn profile extraction capabilities powered by the [Lakome API](https://mcp.lakome.in).

This server acts as a bridge between LLM clients (such as Claude Desktop, Cursor, Cline, Roo Code, and custom AI agents) and the Lakome LinkedIn intelligence endpoint.

---

## ⚡ Features

- **Standard stdio Transport**: Compatible with any standard MCP client.
- **Single Specialized Tool**: Exposes `extract_linkedin_profile` to extract full structured profile details (work experience, education, skills, headline, summary, contact info, and more).
- **Batch Processing**: Supports querying single or multiple LinkedIn profile URLs in a single request.
- **Error Handling**: Validates authentication keys and returns formatted error feedback.

---

## 📋 Prerequisites

- **Node.js** v18.0.0 or higher
- A **Lakome API Key** (Get yours at [mcp.lakome.in](https://mcp.lakome.in))

---

## 🔑 Setting Your `LAKOME_API_KEY`

The server requires your `LAKOME_API_KEY` to authenticate requests with the Lakome API endpoint.

### On macOS / Linux
```bash
export LAKOME_API_KEY="your_actual_lakome_api_key_here"
```

### On Windows (PowerShell)
```powershell
$env:LAKOME_API_KEY="your_actual_lakome_api_key_here"
```

### On Windows (Command Prompt)
```cmd
set LAKOME_API_KEY=your_actual_lakome_api_key_here
```

---

## 🚀 Installation & Client Configuration

### 1. Claude Desktop Setup

Add the server configuration to your `claude_desktop_config.json`:

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

```json
{
  "mcpServers": {
    "lakome-linkedin": {
      "command": "node",
      "args": [
        "/absolute/path/to/mcp-server/index.js"
      ],
      "env": {
        "LAKOME_API_KEY": "your_actual_lakome_api_key_here"
      }
    }
  }
}
```

> **Note for Windows users**: Replace `/absolute/path/to/mcp-server/index.js` with your absolute Windows path (e.g., `D:\\extensions and projects\\lakome API project\\mcp-server\\index.js`).

---

### 2. Cursor IDE Setup

Add the following to your project's `.cursor/mcp.json` or global MCP settings:

```json
{
  "mcpServers": {
    "lakome-linkedin": {
      "command": "node",
      "args": [
        "./mcp-server/index.js"
      ],
      "env": {
        "LAKOME_API_KEY": "your_actual_lakome_api_key_here"
      }
    }
  }
}
```

---

### 3. Smithery.ai CLI

You can install and run the server automatically via [Smithery](https://smithery.ai):

```bash
npx -y @smithery/cli install @lakome/linkedin-mcp --client claude
```

---

## 🛠️ Tool Reference

### `extract_linkedin_profile`

Extracts comprehensive, structured profile data and intelligence from one or more LinkedIn profile URLs.

#### Parameters

| Name | Type | Required | Description |
| :--- | :--- | :--- | :--- |
| `profileUrls` | `string[]` | **Yes** | Array of LinkedIn profile URLs to extract (e.g. `["https://www.linkedin.com/in/williamhgates"]`) |

#### Example Invocation

```json
{
  "profileUrls": [
    "https://www.linkedin.com/in/williamhgates",
    "https://www.linkedin.com/in/satyanadella"
  ]
}
```

#### Example Output Response

```json
[
  {
    "url": "https://www.linkedin.com/in/williamhgates",
    "data": {
      "fullName": "Bill Gates",
      "headline": "Co-chair, Bill & Melinda Gates Foundation",
      "location": "Seattle, Washington, United States",
      "summary": "Co-chair of the Bill & Melinda Gates Foundation. Founder of Breakthrough Energy...",
      "experiences": [
        {
          "title": "Co-chair",
          "company": "Bill & Melinda Gates Foundation",
          "dateRange": "2000 - Present"
        }
      ],
      "education": [
        {
          "schoolName": "Harvard University",
          "degreeName": "Honorary Doctorate",
          "fieldOfStudy": "Law"
        }
      ],
      "skills": ["Philanthropy", "Software Development", "Global Health"]
    },
    "status": "success"
  }
]
```

---

## 🧪 Local Testing & Development

1. **Install dependencies**:
   ```bash
   cd mcp-server
   npm install
   ```

2. **Run server locally**:
   ```bash
   LAKOME_API_KEY="your_api_key" node index.js
   ```

3. **Inspect with MCP Inspector**:
   ```bash
   npx @modelcontextprotocol/inspector node index.js
   ```

---

## 📄 License

MIT © [Lakome](https://mcp.lakome.in)