LinkedIn 广告 MCP 服务器，具备完全写作权限：涵盖活动、创意、受众、转化和分析的 25 个工具。可从 Claude、ChatGPT 或光标中创建、更新和删除。
概览
一个MCP（模型上下文协议）服务器，能够访问和分析您的LinkedIn广告数据。为希望利用AI进行活动优化、绩效报告和数据驱动广告决策的营销人员、创始人和增长团队打造。 同一作者：是托管的 LinkedIn 广告主页。用 OAuth 登录（无 LinkedIn 开发者应用，无需管理凭证），约两分钟内连接 Claude、ChatGPT 或光标，即可在同一接口上使用 Google Ads 和 Microsoft Ads。阅读工具免费;每次写入前都会预览。这台开源服务器保持免费且自托管。 只需复制下面的一个提示并粘贴到Claude中即可。AI会帮你完成一切！
概述（AI 翻译）
一个MCP（模型上下文协议）服务器，使Claude AI能够访问和分析您的LinkedIn广告数据。为希望利用AI进行活动优化、绩效报告和数据驱动广告决策的营销人员、创始人和增长团队打造。
[!提示] 想要无需任何设置就实现吗？ 同一作者：AdPlug 是托管的 LinkedIn 广告 MCP。使用 OAuth 登录（无需LinkedIn开发者应用，无需管理凭证），连接 Claude、ChatGPT 或光标，约两分钟内即可在同一连接器上使用 Google Ads 和 Microsoft 广告。阅读工具免费;每次写入都会在运行前预览。这个开源服务器保持免费且自托管。
快速安装（无需编码！）
**不想处理技术问题？**只需复制下面的一个提示并粘贴到Claude中即可。AI会帮你完成一切！
选项1：使用Claude代码安装（推荐）
如果你安装了Claude代码，只需复制粘贴整个提示：
点击展开 Claude Code 安装提示
选项2：使用Claude桌面安装（基于聊天）
本页由 AI 翻译，技术细节请以原文为准。
README
以下为原文 README 节选，完整内容请查看原文。
LinkedIn Ads MCP Server
An MCP (Model Context Protocol) server that enables Claude AI to access and analyze your LinkedIn Ads data. Built for marketers, founders, and growth teams who want to leverage AI for campaign optimization, performance reporting, and data-driven advertising decisions.
[!TIP] Want this without any setup? From the same author: AdPlug is the hosted LinkedIn Ads MCP. Sign in with OAuth (no LinkedIn developer app, no credentials to manage), connect Claude, ChatGPT, or Cursor in about two minutes, and get Google Ads and Microsoft Ads on the same connector. Read tools are free; every write is previewed before it runs. This open-source server stays free and self-hosted.
Quick Install (No Coding Required!)
Don’t want to deal with technical stuff? Just copy one of the prompts below and paste it into Claude. The AI will do everything for you!
Option 1: Install with Claude Code (Recommended)
If you have Claude Code installed, just copy and paste this entire prompt:
I want you to install the LinkedIn Ads MCP server so I can analyze my LinkedIn advertising data. Please do the following:
1. FIRST, check if Node.js is installed by running `node --version`. If not installed, tell me to install it from https://nodejs.org first.
2. Clone the repository to my home directory:
- cd ~
- git clone https://github.com/danielpopamd/linkedin-ads-mcp.git
- cd linkedin-ads-mcp
3. Install dependencies and build:
- npm install
- npm run build
4. Create the .env file with placeholder values:
- cp .env.example .env
5. NOW IMPORTANT - Ask me for my LinkedIn API credentials:
- Ask: "Please provide your LinkedIn Client ID (from https://www.linkedin.com/developers/apps)"
- Ask: "Please provide your LinkedIn Client Secret"
6. Update the .env file with the credentials I provide.
7. Set up Claude Desktop configuration:
- Read the current Claude Desktop config file:
- macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
- Windows: %APPDATA%/Claude/claude_desktop_config.json
- Add the linkedin-ads MCP server to mcpServers (merge with existing config if any):
{
"mcpServers": {
"linkedin-ads": {
"command": "node",
"args": ["/linkedin-ads-mcp/dist/index.js"],
"env": {
"LINKEDIN_CLIENT_ID": "",安装
This server does not publish a one-line install command.
Open the repository installation guide 新手？先看 mcpskill.org 教程 →配置
{
"mcpServers": {
"linkedin-ads": {
"command": "node",
"args": ["/full/path/to/linkedin-ads-mcp/dist/index.js"],
"env": {
"LINKEDIN_CLIENT_ID": "your_client_id",
"LINKEDIN_CLIENT_SECRET": "your_client_secret"
}
}
}
}