Bohea

Managing Google Ads campaigns in plain English 用一句自然语言,管理 Google Ads 广告

A Model Context Protocol (MCP) server that connects Claude Desktop directly to the Google Ads API — pause campaigns, move budgets, and adjust keyword bids by just asking. 一个把 Claude Desktop 直连 Google Ads API 的 MCP 服务器——暂停广告系列、调预算、改关键词出价,开口说一句就行。

PythonMCPGoogle Ads APIOAuth 2.0Claude Desktop

The problem问题

Day-to-day Google Ads management is a loop of clicking through the same dashboard screens: check performance, pause the loser, raise the budget on the winner, tweak a bid. Each step is trivial; the loop is a time sink — and the Ads UI buries simple actions under layers of navigation. 日常的 Google Ads 管理,就是在同样几个后台页面里循环点击:看效果、停掉亏的、给赚的加预算、微调出价。每一步都不难,循环起来就是时间黑洞——而 Ads 的界面偏偏把简单操作埋在层层导航之下。

The constraint约束

Google's Ads API is powerful but hostile to casual use: OAuth flows, developer tokens, customer IDs, YAML configs. The goal was to hide all of that behind natural language, without compromising on real API correctness — and to be demonstrable before any credentials existed. Google Ads API 很强大,但对轻度使用者极不友好:OAuth 流程、开发者令牌、客户 ID、YAML 配置。目标是把这一切藏到自然语言背后,同时不牺牲真实 API 调用的正确性——并且要在任何凭据存在之前就能演示。

The solution方案

An MCP server exposing seven tools to Claude Desktop: 向 Claude Desktop 暴露 7 个工具的 MCP 服务器:

So "pause campaign 1002" or "raise the daily budget of campaign 1001 to $65" become things you say, not workflows you click through. 于是"暂停 1002 号广告系列""把 1001 的日预算提到 65 美元",都变成说出来的事,而不是一层层点出来的流程。

The design decision that sells it: mock mode真正打动客户的设计:Mock 模式

The server ships with a built-in simulation mode. With no credentials at all, it serves realistic campaign data — so the full experience is demonstrable in Claude Desktop in minutes, before touching a live ad account. Going live is then a config flip: an interactive OAuth helper script generates the token and writes the config for you. 服务器内置模拟模式:在完全没有凭据的情况下,也能返回逼真的广告数据——几分钟内就能在 Claude Desktop 里体验完整功能,而不用碰任何真实广告账户。上线只是拨一下配置开关:交互式 OAuth 助手脚本会自动生成令牌并写好配置。

This is a pattern I use deliberately: the client sees the working product first, and connects real credentials last. Trust flows from demonstration, not from promises. 这是我刻意坚持的模式:客户先看到能跑的产品,最后才接入真实凭据。信任来自演示,而不是承诺。

Proof证明

Google Ads MCP architecture overview diagram
Architecture: Claude Desktop ⇄ MCP server ⇄ Google Ads API, with mock-mode isolation. 架构:Claude Desktop ⇄ MCP 服务器 ⇄ Google Ads API,Mock 模式隔离。

Delivered with the full documentation set: technical specification, setup-and-verification guide with screenshots, developer notes, and a one-click Windows setup script — in both English and Chinese. Including the troubleshooting nobody writes down (Google's "unverified app" screen, testing-mode OAuth audiences). 随附完整文档交付:技术规格书、带截图的安装验证指南、开发者笔记、Windows 一键安装脚本——中英双语。还包括没人愿意写下来的疑难排查(Google 的"未验证应用"拦截页、测试模式的 OAuth 受众配置)。

Where else this applies还能用在哪

Any API your team touches daily through a clunky dashboard can become an MCP server: ad platforms, CRMs, e-commerce backends, internal admin panels. If your team already uses Claude, they can operate these systems by asking. 任何你的团队每天都要通过笨重后台去碰的 API,都可以做成 MCP 服务器:广告平台、CRM、电商后台、内部管理面板。如果团队已经在用 Claude,以后这些系统开口问一句就能操作。

← All case studies← 全部案例