# LinkedIn MCP (by TalkToHumans)

Connects AI assistants to LinkedIn messages and contacts. It searches connections, enriches profiles, and stages message drafts for manual approval.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 26
- Author: TalkToHumans
- License: MIT · policy=link-only · description only; the file stays with the author
- Source: https://github.com/TalkToHumans/linkedin-mcp
- Updated: 2026-10-24
- HTML: https://affpapa.org/en/nevibecode/mcp/linkedin-mcp-by-talktohumans

## What it does

This MCP server links AI assistants to a LinkedIn profile through the remote endpoint `https://api.talktohumans.app/mcp`. It reads from a synchronized cache rather than making direct requests every time. Actions run inside your normal browser extension. This setup avoids cloud automation and proxy addresses.

The server helps locate unanswered threads, evaluate connections, and draft outreach. It stages follow-up messages and replies for your review. It never hits send on its own. Every outgoing message requires manual approval.

Using the server requires a TalkToHumans Pro subscription and the companion extension. Built-in daily action caps cannot be overridden by prompts. Once a limit is reached, that action pauses until the next day.

## Requirements
- Remote server: `https://api.talktohumans.app/mcp`
- Works with: LinkedIn

## Install

### Claude Code (native platform)

**Platform CLI: remote server**
```bash
claude mcp add --transport http linkedin-mcp https://api.talktohumans.app/mcp
```

### Codex

**Platform CLI: remote server**
```bash
codex mcp add linkedin-mcp-by-talktohumans --url https://api.talktohumans.app/mcp
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "linkedin-mcp-by-talktohumans": {
            "url": "https://api.talktohumans.app/mcp"
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "linkedin-mcp-by-talktohumans": {
            "type": "http",
            "url": "https://api.talktohumans.app/mcp"
        }
    }
}
```

### Gemini CLI

**Platform CLI: remote server**
```bash
gemini mcp add -t http linkedin-mcp-by-talktohumans https://api.talktohumans.app/mcp
```

## When to use it
- Identify threads requiring a response in LinkedIn and Sales Navigator
- Score existing connections against customer profile criteria
- Draft personalized replies and staged follow-up sequences
- Retrieve work email addresses and phone numbers for contacts

## Example prompts
- Check my LinkedIn inbox and list threads waiting for my reply
- Find marketing directors in my network and draft initial outreach messages

## Similar
- [labelhead-artist-momentum](https://affpapa.org/en/nevibecode/mcp/labelhead-artist-momentum.md) — MCP server · ★ 107423
- [openshorts](https://affpapa.org/en/nevibecode/mcp/openshorts.md) — MCP server · ★ 7049
- [OpenScreen](https://affpapa.org/en/nevibecode/mcp/openscreen.md) — MCP server · ★ 4863
- [Usertour MCP Server](https://affpapa.org/en/nevibecode/mcp/usertour-mcp-server.md) — MCP server · ★ 2326
- [Appllama](https://affpapa.org/en/nevibecode/mcp/appllama.md) — MCP server · ★ 3046
- [obsei](https://affpapa.org/en/nevibecode/mcp/obsei.md) — MCP server · ★ 1441

---
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