# linkedin-mcp

A local MCP server that drives your logged-in Chrome profile and hands the agent LinkedIn profiles, jobs, companies and inbox threads as JSON.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 12
- Author: devag7
- License: MIT · policy=link-only · description only; the file stays with the author
- Source: https://github.com/devag7/linkedin-mcp
- Updated: 2026-10-22
- HTML: https://affpapa.org/en/nevibecode/mcp/linkedin-mcp

## What it does

Under the hood the server keeps a persistent Google Chrome profile through Patchright and fires Voyager requests from the page you are already signed in to. Replies get reshaped into JSON for the MCP client. A few discovery tools read page data as a fallback.

Alpha writes stay off unless you turn them on. All five of them want a preview token issued by the server plus `confirm:true`, draw on attempt budgets, and can answer with `unknown` when completion cannot be confirmed. Nothing here fills in or sends job applications.

This is an unofficial integration, and LinkedIn can restrict accounts that use it. Endpoint names, query IDs and response shapes shift without notice, so a tool that worked last month may just break. Run it against a side browser profile rather than the one you use daily.

## Requirements
- Needs: Node.js (commands run via npx)
- Works with: LinkedIn

## Install

### Claude Code (native platform)

**Platform CLI**
```bash
claude mcp add linkedin-mcp -- npx -y linkedin-mcp-tools
```

### Codex

**Platform CLI**
```bash
codex mcp add linkedin-mcp -- npx -y linkedin-mcp-tools
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "linkedin-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "linkedin-mcp-tools"
            ]
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "linkedin-mcp": {
            "type": "stdio",
            "command": "npx",
            "args": [
                "-y",
                "linkedin-mcp-tools"
            ]
        }
    }
}
```

### Gemini CLI

**Platform CLI**
```bash
gemini mcp add linkedin-mcp npx -y linkedin-mcp-tools
```

## When to use it
- turn candidate and company profiles into structured JSON
- export a job search result set without copy-pasting by hand
- read LinkedIn inbox threads from inside the chat
- check company details before replying to a recruiter
- pull profile notes for several leads in one agent run

## Example prompts
- Pull the LinkedIn profile for this company and list its key people
- Find `backend engineer` job posts from the past week and put them in a table
- Go through my LinkedIn inbox and flag the unread threads

## Similar
- [Scrapling MCP Server](https://affpapa.org/en/nevibecode/mcp/scrapling-mcp-server.md) — MCP server · ★ 89433
- [browser-use](https://affpapa.org/en/nevibecode/mcp/browser-use.md) — MCP server · ★ 119160
- [AIHawk](https://affpapa.org/en/nevibecode/mcp/aihawk.md) — MCP server · ★ 32221
- [Skyvern](https://affpapa.org/en/nevibecode/mcp/skyvern.md) — MCP server · ★ 23263
- [SeleniumBase MCP](https://affpapa.org/en/nevibecode/mcp/seleniumbase-mcp.md) — MCP server · ★ 13169
- [apify-mcp-server](https://affpapa.org/en/nevibecode/mcp/apify-mcp-server.md) — MCP server · ★ 12927

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md