Tencent Ad Server
FreeNot checkedWraps all Tencent Ads Marketing API v3.0 endpoints as MCP tools, enabling AI assistants to directly manage ads, creatives, reports, and more via natural languag
About
Wraps all Tencent Ads Marketing API v3.0 endpoints as MCP tools, enabling AI assistants to directly manage ads, creatives, reports, and more via natural language.
README
English | 中文
腾讯广告 MCP Server
将腾讯广告 Marketing API v3.0 全部接口封装为 MCP (Model Context Protocol) 工具,让 AI 助手(Claude Code、Claude Desktop 等)直接操作腾讯广告。
特性
- 358 个 MCP 工具,覆盖腾讯广告 Marketing API v3.0 全部接口
- 核心模块(广告组、创意、报表等)手写精细 schema,其余从官方 Go SDK 自动生成
- OAuth token 自动刷新 + 本地持久化
- 支持 Claude Code / Claude Desktop / 任何 MCP 客户端
覆盖模块
| 模块 | 说明 |
|---|---|
| 广告组 (adgroups) | 创建、查询、更新、删除、调价、调预算、暂停/启动 |
| 创意 (dynamic_creatives) | 创建、查询、更新、删除创意 |
| 素材 (images/videos) | 图片和视频的上传、查询、删除 |
| 报表 (reports) | 日报、时报、异步报表任务 |
| 人群 (audiences) | 自定义人群管理、定向查询 |
| 资金 (funds) | 账户余额查询、资金划转 |
| 线索 (leads) | 线索列表、创建、认领 |
| 账户 (advertiser) | 账户信息、日预算管理 |
| 更多... | 微信渠道、落地页、转化追踪、批量操作、AI素材 等 200+ 接口 |
安装
git clone https://github.com/andyleimc-source/tencent-ad-mcp.git
cd tencent-ad-mcp
npm install
npm run build
Claude Code
推荐(使用编译产物,启动快、无额外依赖):
claude mcp add --scope user tencent-ad -- node /path/to/tencent-ad-mcp/dist/index.js
开发模式(需要 tsx)
claude mcp add --scope user tencent-ad -- npx tsx /path/to/tencent-ad-mcp/src/index.ts
注意:如果
tsx未全局安装,npx需要下载依赖,可能导致启动超时。
Claude Desktop
在 claude_desktop_config.json 中添加:
{
"mcpServers": {
"tencent-ad": {
"type": "stdio",
"command": "node",
"args": ["/path/to/tencent-ad-mcp/dist/index.js"],
"env": {
"TENCENT_AD_CLIENT_ID": "your_app_id",
"TENCENT_AD_CLIENT_SECRET": "your_client_secret",
"TENCENT_AD_ACCESS_TOKEN": "your_access_token",
"TENCENT_AD_REFRESH_TOKEN": "your_refresh_token",
"TENCENT_AD_ACCOUNT_ID": "your_account_id"
}
}
}
}
环境变量
| 变量 | 必填 | 说明 |
|---|---|---|
TENCENT_AD_CLIENT_ID |
是 | OAuth 应用 ID |
TENCENT_AD_CLIENT_SECRET |
是 | OAuth 应用密钥 |
TENCENT_AD_ACCESS_TOKEN |
是 | 访问令牌 |
TENCENT_AD_REFRESH_TOKEN |
是 | 刷新令牌 |
TENCENT_AD_ACCOUNT_ID |
否 | 默认广告主账户 ID |
TENCENT_AD_TOKEN_FILE |
否 | Token 持久化路径(默认 ~/.tencent-ad-token.json) |
获取凭证
- 注册腾讯广告开发者:https://developers.e.qq.com
- 创建应用,获取
client_id和client_secret - 在开发者工具页面获取
access_token和refresh_token - 在广告投放后台 (e.qq.com) 获取
account_id
开发
npm run dev # 开发模式(tsx 直接运行)
npm run build # 编译 TypeScript
npm run start # 运行编译产物
重新生成工具(需要先克隆官方 Go SDK):
git clone --depth 1 https://github.com/TencentAd/marketing-api-go-sdk.git /tmp/marketing-api-go-sdk
npm run generate
License
Apache-2.0
关注我

雷码工坊笔记 — 微信扫码关注
Install Tencent Ad Server in Claude Desktop, Claude Code & Cursor
unyly install tencent-ad-mcp-serverInstalls into Claude Desktop, Claude Code, Cursor & VS Code — handles npx, uvx and build-from-source repos for you.
First time? Get the CLI: curl -fsSL https://unyly.org/install | sh
Or configure manually
Run in your terminal:
claude mcp add tencent-ad-mcp-server -- npx -y tencent-ad-mcpFAQ
Is Tencent Ad Server MCP free?
Yes, Tencent Ad Server MCP is free — one-click install via Unyly at no cost.
Does Tencent Ad Server need an API key?
No, Tencent Ad Server runs without API keys or environment variables.
Is Tencent Ad Server hosted or self-hosted?
A hosted option is available: Unyly runs the server in the cloud, no local setup required.
How do I install Tencent Ad Server in Claude Desktop, Claude Code or Cursor?
Open Tencent Ad Server on unyly.org, pick your client tab (Claude Desktop, Claude Code, Cursor) and press Install — the config is generated automatically, no JSON editing.
Related MCPs
Fetch
Web content fetching and conversion for efficient LLM usage.
AWS KB Retrieval
Retrieval from AWS Knowledge Base using Bedrock Agent Runtime.
by modelcontextprotocolSpring AI MCP Server
Provides auto-configuration for setting up an MCP server in Spring Boot applications.
llm-analysis-assistant
A very streamlined mcp client that supports calling and monitoring stdio/sse/streamableHttp, and can also view request responses through the /logs page. It also
by xuzexin-hzCompare Tencent Ad Server with
Not sure what to pick?
Find your stack in 60 seconds
Author?
Embed badge for your README
Browse similar
All ai MCPs
