能做什么
Google Ads for AI agents: live reports, Keyword Planner, and changes with preview, confirm and undo.
作者提供的原文
- 连接方式 在云端运行
- 账号或密钥 连接时登录该服务(OAuth)
- 分类 营销与社交媒体
可搭配使用
教 AI 做这类工作的 Skill,可与本项一起使用
为什么排在这里
此项在“连接 AI 的应用”标签中,该标签不使用星标,按以下顺序排列
| 1. 在 Claude 连接器目录中 | 否 | |
|---|---|---|
| 2. 团队实测过 | 否 | |
| 3. 适合泰国用户 | 否 | |
| 4. 不计星标的使用量 | 20/100 | 热度 0 · 新鲜度 12 · 仍在响应 8 · 用户喜欢 +0 |
| 5. 登记日期 | 2026-11-19 |
用户喜欢: 0 · 最多加 5 分(每人 1 分),不能用钱买。
质量: 基础检查通过 4/4 项(仅展示,不用于排序)
安装
选择你使用的 AI 应用,然后复制设置。
用一句话让 AI 帮你安装
请帮我安装 Querya — Google Ads。按照 https://mcp.popnx.com/i/querya.md 操作,先把命令给我看,等我同意后再运行。粘贴到能在你电脑上工作的 AI(如 Claude Code、Cursor)。它会读取我们的步骤,先给你看命令,等你同意。无需密钥,无需注册。 · 查看 AI 会读取的全文
通过 4/4 项检查 · 你的提问会经过开发者的服务器(mcp.querya.io) · ✓ 命令已检查 2026年11月19日
第一步:你用哪个 AI?
选择你用的应用,步骤会显示在下方。
可连接 Claude · 约 2 分钟
不需要密钥,不用安装程序 · 在 claude.ai 或桌面应用设置一次,即可在聊天中使用 · 免费账户可添加 1 个 · Team/Enterprise 方案由所有者(Owner)添加
打开 Claude 的 Connectors 页面
CustomizeConnectors
点击“Add” → “Custom” → “Web”,填写这 2 项
把这里的内容复制到 Claude 中同名的输入框,然后点击 Continue
Name · 名称Querya — Google AdsRemote MCP server URL · 地址https://mcp.querya.io/mcp在 Claude 检测到的登录设置页点击 Continue · Authentication 按作者说明选择(Sign in now、Sign in when needed 或 No sign in),然后点击 Add
在聊天中开启
+ConnectorsQuerya — Google Ads
试一试
用 Querya — Google Ads 告诉我你能帮我做什么,然后做一件给我看✓ 如果 Claude 说正在使用 Querya — Google Ads,或回答中出现 Querya — Google Ads 的工具名称,就表示连接成功
菜单名称已于 2026年11月11日 对照 Anthropic 帮助页面核实 · 你的界面可能因版本略有不同
能否连接 ChatGPT 取决于方案
完整 MCP:网页版 ChatGPT Business、Enterprise 或 Edu · Pro:以读取/获取权限连接,修改数据的工具可能用不了 · Plus:官方文档尚未确认,如果在插件页看到添加自定义 MCP 的选项可以试试 · 仅限网页
在网页版 ChatGPT 打开添加 MCP 的页面
Plugins+Add custom MCP server
填写名称和地址
输入名称,在 Connection 下粘贴地址,勾选风险提示,然后点击 Create as a plugin
Name · 名称Querya — Google AdsConnection · 地址https://mcp.querya.io/mcp在聊天中选择 Querya — Google Ads
开启新聊天,输入前先从插件列表中选择 Querya — Google Ads
试一试
用 Querya — Google Ads 告诉我你能帮我做什么,然后做一件给我看✓ 如果 ChatGPT 说正在使用 Querya — Google Ads,或回答中出现 Querya — Google Ads 的工具名称,就表示连接成功
菜单名称已于 2026年11月11日 对照 OpenAI 帮助页面核实 · 你的界面可能因版本略有不同
可连接 Claude Code · 约 2 分钟
不需要密钥,不用安装程序
打开终端
Mac:按 Command+空格,输入 Terminal · Windows:打开 PowerShell
粘贴这条命令并按 Enter
claude mcp add --transport http --scope user querya https://mcp.querya.io/mcp在 Claude Code 中输入 /mcp
应能看到 Querya — Google Ads 在列表中并显示已连接
试一试
用 Querya — Google Ads 告诉我你能帮我做什么,然后做一件给我看✓ 如果 Claude Code 说正在使用 Querya — Google Ads,或回答中出现 Querya — Google Ads 的工具名称,就表示连接成功
菜单名称已于 2026年11月11日 对照 Anthropic 帮助页面核实 · 你的界面可能因版本略有不同
可连接 Cursor · 约 2 分钟
不需要密钥,不用安装程序
在 Cursor 中以 Agent 模式打开 AI 聊天
试一试
用 Querya — Google Ads 告诉我你能帮我做什么,然后做一件给我看✓ 如果 Cursor 说正在使用 Querya — Google Ads,或回答中出现 Querya — Google Ads 的工具名称,就表示连接成功
菜单名称已于 2026年11月11日 对照 Cursor 帮助页面核实 · 你的界面可能因版本略有不同
可连接 VS Code · 约 2 分钟
不需要密钥,不用安装程序
在 VS Code 中以 Agent 模式打开 AI 聊天
试一试
用 Querya — Google Ads 告诉我你能帮我做什么,然后做一件给我看✓ 如果 VS Code 说正在使用 Querya — Google Ads,或回答中出现 Querya — Google Ads 的工具名称,就表示连接成功
菜单名称已于 2026年11月11日 对照 VS Code 帮助页面核实 · 你的界面可能因版本略有不同
其他支持 MCP 的应用(如 Windsurf、Zed、Gemini CLI)添加方式各不相同,请在应用列表中查看
通过网页连接的应用使用的地址
https://mcp.querya.io/mcpJSON 设置在下方“开发者专用”中
开发者专用:终端命令和 JSON 设置
通过网页连接
Claude Code
claude mcp add --transport http --scope user querya https://mcp.querya.io/mcpCursor (~/.cursor/mcp.json)
{
"mcpServers": {
"querya": {
"url": "https://mcp.querya.io/mcp"
}
}
}VS Code (mcp.json)
{
"servers": {
"querya": {
"type": "http",
"url": "https://mcp.querya.io/mcp"
}
}
}这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同,请以 README 为准。
一览
哪些应用可以使用它
依据这个服务器的连接方式和各应用自己的文档,检查于 2026年11月10日。
通过互联网连接,适用于
ClaudeChatGPTGooseLM StudioMsty StudioCherry StudioCursorVS Code + GitHub CopilotVisual StudioWindsurf (Devin Desktop)ZedKiroClineContinueJetBrains AI AssistantClaude CodeCodex CLIGemini CLIOpenCodenodecodeWarpLibreChatOpen WebUIRaycast
它能做什么
服务器要求先登录,才会列出它的工具。
基础检查i
我们检查的是任何人都能看到的信息;我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月20日
- ✓ 通过
作者与仓库一致
注册名称已通过域名 querya.io 验证(注册中心会核实域名所有权)
- ✓ 通过
仍在维护
代码最后更新于昨天
- – 不适用
有许可证
不适用:由 querya.io 的所有者自己运行的云端服务器,你不会运行仓库里的代码
- ✓ 通过
端点有响应
在 507 毫秒内响应(HTTP 401)
- ✓ 通过
使用 OAuth 登录
声明支持 OAuth 登录,你的 AI 应用可以带你去登录
- … 尚未检查
工具描述中没有隐藏指令
尚未检查;我们会在检查端点时读取工具列表
作者:申请重新检查或报告信息错误
给作者:在 README 中加徽章
如果你是作者,可把这段代码贴到 README。徽章会链接回本页。
[](https://mcp.popnx.com/en/servers/querya)讨论
提问、分享技巧或报告无法使用。按“有帮助”数量排序。
用户评价
还没有评价
与“营销与社交媒体”中的其他服务器比较i
- 星标数多于此分类中其他 4243 个服务器的 0%
- 发布到注册中心的时间比此分类中其他 4243 个服务器的 97% 更新
- 基础检查结果等于或优于此分类中其他 4243 个服务器的 99%
与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时,星标数才计入。
常见问题
Querya — Google Ads 安全吗?
它在 4 项适用的基础检查中通过了 4 项。我们没有阅读代码。在添加密钥或令牌之前,请先看看这个服务器要求哪些权限,并使用只具备所需权限的密钥。
它需要哪些密钥或代码?
注册中心没有列出必需的密钥,不过有些服务器会在首次使用时要求你登录。
它在我的电脑上运行还是在云端?
它在作者的云端运行。通过互联网连接,无需安装,但你发送的内容会经过作者的服务器。
它还在维护吗?
GitHub 仓库最后更新于昨天,最新版本(1.0.1)于昨天进入注册中心。
哪些应用可以使用它?
支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。它通过 URL 连接,因此也能用于接受远程 MCP 的应用,例如网页版 ChatGPT(Business 及以上为完整 MCP;Pro 为只读)。
有什么可以替代它?
同一分类中有:Relaticle, ChatbotX, X (Twitter) MCP Server by Xquik, Betterlytics, BibiGPT YouTube Video Summarizer
功能相近的其他选择
同一分类、其他作者、命令已通过检查。官方的排在前面,再按星标排序。
如何看卡片:↓ 每周下载量i★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i
Relaticle
Open-source CRM your AI agents can write to: companies, people, opportunities, tasks and notes.
ChatbotX
Omnichannel customer messaging, CRM contacts, flows, sequences, broadcasts, and AI automation.
X (Twitter) MCP Server by Xquik
Xquik is the world's fastest and cheapest X (Twitter) data API with the most complete X data.
Betterlytics
Query your Betterlytics web analytics from AI agents: traffic, funnels, journeys, errors, uptime.
BibiGPT YouTube Video Summarizer
AI video summarizer: summarize and transcribe YouTube, Bilibili, TikTok and podcast videos.
| 本项 Querya — Google Ads | Relaticle | ChatbotX | X (Twitter) MCP Server by Xquik | Betterlytics | BibiGPT YouTube Video Summarizer | |
|---|---|---|---|---|---|---|
| 运行位置 | 在云端运行,无需安装 | 在云端运行,无需安装 | 在云端运行,无需安装 | 在云端运行,无需安装 | 在云端运行,无需安装 | 在云端运行,无需安装 |
| 需要密钥 | 否 | 否 | 否 | 否 | 是 | 否 |
| 可在 Claude 中按 + 添加 | 否 | 否 | 否 | 否 | 否 | 否 |
| 基础检查 | 4/4 | 4/4 | 4/4 | 4/4 | 4/4 | 4/4 |
| 许可证 | MIT | AGPL-3.0 | NOASSERTION | MIT | AGPL-3.0 | MIT |
| 价格 | 登记中未列出费用 | 登记中未列出费用 | 登记中未列出费用 | 登记中未列出费用 | 登记中未列出费用 | 登记中未列出费用 |
作者的 README
打开 README
按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。
Querya: Google Ads MCP server
Querya is a hosted MCP server that connects AI agents to your Google Ads accounts: Claude, ChatGPT, Cursor, VS Code, Gemini CLI, Cline and any client that speaks MCP over Streamable HTTP.
Ask in plain language and your agent answers with live data: performance by campaign, ad group, keyword or search term; wasted spend and negative keyword candidates; Quality Score; impression share; budget pacing; conversion actions; change history; policy issues and Google Ads Recommendations. Keyword research uses Google Keyword Planner: ideas, metrics and forecasts by location and language.
Changes are safe by design. Creating campaigns, ads, keywords, negatives, assets and audiences, or editing budgets, bids, targeting and status, never applies directly. Querya first returns a preview validated by Google Ads, with the risk level and the daily spend impact. Nothing changes until you confirm. New campaigns are always created paused. Per-account guardrails cap budgets and bids and block removals by default. Every change is logged and can be undone.
- Server URL:
https://mcp.querya.io/mcp(Streamable HTTP) - Auth: OAuth 2.1 with PKCE. Dynamic client registration and Client ID Metadata Documents are supported, so there is no key to paste. You sign in with Google and choose exactly which Google Ads accounts the agent can reach.
- Plans: Free: 1 account, read-only. Pro and Max: more accounts, manager (MCC) accounts and changes. See querya.io.
This repository holds the public listing files (MCP Registry server.json, Gemini CLI extension). The server itself is hosted by Querya; there is nothing to install or run.
Connect
Claude (claude.ai and Claude Desktop)
Settings → Connectors → Add custom connector → URL https://mcp.querya.io/mcp.
Claude Code
claude mcp add --transport http querya https://mcp.querya.io/mcp
Cursor
~/.cursor/mcp.json:
{
"mcpServers": { "querya": { "url": "https://mcp.querya.io/mcp" } } }
VS Code (GitHub Copilot)
.vscode/mcp.json:
{
"servers": { "querya": { "type": "http", "url": "https://mcp.querya.io/mcp" } } }
Gemini CLI
gemini extensions install https://github.com/extractify/querya-mcp
Cline, Windsurf and other clients
Add a remote MCP server with the URL https://mcp.querya.io/mcp. The client opens the Querya sign-in in your browser the first time.
ChatGPT
Settings → Apps & Connectors → developer mode → Create → URL https://mcp.querya.io/mcp, authentication OAuth.
Example prompts
- "How did my campaigns do last week compared with the week before?"
- "Which search terms spent money without converting in the last 30 days? Prepare negatives for the worst ones."
- "Find keyword ideas for 'curso de inglês online' in Brazil and forecast clicks and cost for R$50/day."
- "Raise the budget of the Brand campaign to R$80/day." (shows a preview; nothing changes until you confirm)
- "Who changed what in this account this week?"
Tools (59)
Read tools have readOnlyHint. Write tools only prepare a validated plan; confirm_change_plan (destructiveHint) is the one that changes the account, after your explicit confirmation.
| Tool | What it does |
|---|---|
list_accounts | List the Google Ads accounts the user has enabled for Querya, with currency, time zone, whether each one is a manager (MCC) account, and whether write tools are allowed on it. |
get_account_hierarchy | Show the manager (MCC) tree: every Google Ads account Querya found for the user, its parent manager, and whether it is enabled in Querya. |
get_account_overview | Quick health check of one account: status, spend, clicks, conversions, CPA and ROAS for the period, number of active campaigns, the top 5 campaigns by cost, and counts of disapproved or limited ads. |
set_default_account | Choose the account used when other tools are called without customer_id. |
refresh_accounts | Re-read the accounts the user's Google login can access (including MCC sub-accounts). |
run_gaql | Run a custom read-only Google Ads Query Language (GAQL) query when no ready-made report fits. |
describe_gaql_resource | List the selectable fields (with type, filterable/sortable and enum values), the compatible metrics and segments, and the attributed resources of a GAQL resource, straight from Google Ads metadata. |
get_performance_report | Ready-made performance report by level (account, campaign, ad_group, ad, keyword, bidding_strategy) for a period: impressions, clicks, cost, conversions, value, CTR, avg CPC, CPA and ROAS, optionally split by date or device, with account totals and, if compare=true, change vs the previous period of the same length. |
get_search_terms | Search terms that triggered ads, with matched keyword, cost and conversions, sorted by cost. |
get_asset_performance | Performance of ad assets in the period. |
get_keyword_quality | Quality Score (1–10) and its components — expected CTR, ad relevance, landing page experience — for enabled keywords with traffic in the period, sorted by cost, with the impression-weighted average. |
get_impression_share | Search impression share per Search campaign and the share lost to budget and to rank (ad rank / Quality Score), plus top and absolute-top shares, in percent. |
get_budget_pacing | Month-to-date spend of each enabled campaign against its budget (daily budget × days in month), with a linear projection to month end. |
get_change_history | Changes made to the account, newest first: when, what resource, operation, which tool (web, API, scripts, Querya…) and who. |
get_change_timeline | A readable timeline of what changed in the account and who did it, grouped by day: plain-language sentences ("raised the budget of "Brand" from $50 to $80/day"), current campaign and ad group names, similar changes grouped together, and the change_id of changes made through Querya (for undo_change). |
get_policy_issues | Ads that are disapproved or limited by Google policy, with policy topics and the evidence text. |
get_conversion_actions | Conversion actions of the account (status, type, category, counting, primary or secondary) with all conversions and value in the period. |
get_recommendations | Google Ads Recommendations: Google's active (not dismissed) recommendations with estimated weekly impact on impressions, clicks, cost and conversions, sorted by conversion gain. |
generate_keyword_ideas | Keyword ideas from Google Keyword Planner for seed keywords, a landing page URL, both, or a whole site: average monthly searches, last-month volume, 3-month and year-over-year trend, competition and the top-of-page bid range in the account currency. |
get_keyword_metrics | Historical Keyword Planner metrics for a list of keywords you already have (up to 1000): average monthly searches, trend, competition, top-of-page bids and average CPC; close variants are grouped. |
forecast_keywords | Forecast clicks, cost, average CPC and (when available) conversions and CPA for a NEW Search campaign with the given keywords, daily budget, locations and language, starting tomorrow for 7–90 days. |
search_geo_targets | Find Google Ads location IDs by name (country, state, city, postal code), with canonical name, type and reach. |
search_languages | List Google Ads language IDs and codes, optionally filtered by name or code. |
create_search_campaign | Create a complete Google Search campaign in one step: budget, campaign (ALWAYS created PAUSED), locations, languages, bidding strategy, ad groups with keywords and responsive search ads, and optional campaign negative keywords. |
create_ad_group | Create an ad group in an existing Search campaign, optionally with keywords and responsive search ads. |
create_responsive_search_ad | Create a responsive search ad (3–15 headlines up to 30 characters, 2–4 descriptions up to 90, optional pins and paths). |
add_keywords | Add keywords to an ad group, with match type and optional CPC/final URL. |
add_negative_keywords | Add negative keywords to a campaign, an ad group or a shared negative list (level + target_id). |
create_negative_keyword_list | Create a shared negative keyword list and attach it to campaigns. |
set_status | Enable, pause or remove campaigns, ad groups, ads or keywords (batch). |
update_budget | Change a campaign's daily budget. |
update_bidding_strategy | Switch a campaign bidding strategy (MANUAL_CPC, MAXIMIZE_CLICKS, MAXIMIZE_CONVERSIONS, TARGET_CPA, MAXIMIZE_CONVERSION_VALUE, TARGET_ROAS) and targets, or attach the campaign to an existing portfolio strategy with portfolio_id (see create_bidding_strategy). |
update_bids | Change max CPC bids of ad groups or keywords (Manual CPC). |
update_targeting | Change campaign targeting: add/remove locations and languages (names or IDs), replace the ad schedule, set device bid adjustments (% from -100 to +900). |
update_ad | Edit a responsive search ad: replace headlines and/or descriptions, paths or the final URL. |
update_keywords | Change keyword match type (creates the new keyword and pauses the old one, since match type cannot be edited) or final URL. |
apply_recommendation | Apply Google Ads Recommendations by recommendation_id (from get_recommendations). |
dismiss_recommendation | Dismiss Google Ads Recommendations by recommendation_id (from get_recommendations). |
create_performance_max_campaign | Create a Performance Max campaign in one step: budget, campaign (ALWAYS created PAUSED), locations, languages, bidding (MAXIMIZE_CONVERSIONS / TARGET_CPA / MAXIMIZE_CONVERSION_VALUE / TARGET_ROAS) and one asset group with texts, images, logo, final URL and optional search themes as audience signal. |
create_assets | Create ad assets (extensions) and link them to the account, a campaign or an ad group: sitelinks, callouts, a structured snippet, a call asset, images and business logos (public https URLs, checked by Querya). |
create_conversion_action | Create a conversion action. |
upload_offline_conversions | Import conversions (e.g. |
create_bidding_strategy | Create a portfolio bidding strategy shared by several campaigns: TARGET_CPA, TARGET_ROAS, MAXIMIZE_CONVERSIONS (optional target CPA), MAXIMIZE_CONVERSION_VALUE (optional target ROAS) or MAXIMIZE_CLICKS (optional CPC ceiling). |
bulk_mutate | Advanced: apply a batch of raw Google Ads API mutate operations (GoogleAdsService.Mutate, REST JSON in camelCase, see https://developers.google.com/google-ads/api/docs/mutating/overview) when no specific tool fits, e.g. |
create_audience | Create an audience. |
get_audience_status | Size for Search/Display, match rate and upload job status of an audience list (e.g. |
create_rule | Create a rule that Querya runs on a schedule (daily at an hour of the account time zone, or hourly). |
list_rules | List scheduled rules with their last runs (matches, plan created, applied or failed). |
delete_rule | Delete a scheduled rule (pending plans it created stay until they expire). |
create_alert | Create an email alert for an account (all plans). |
list_alerts | List email alerts with when they were last checked and triggered. |
delete_alert | Delete an email alert. |
confirm_change_plan | Apply a pending change plan AFTER the user explicitly confirmed the preview. |
cancel_change_plan | Discard a pending change plan. |
list_change_plans | List pending (not yet confirmed) change plans of this user. |
| list_change_log | Changes applied through Querya (newest first) with before/after, whether they can be undone, and the Google requ