googleads-automation
Automate Google Ads analytics tasks via Rube MCP (Composio): list Google Ads links, run GA4 reports, check compatibility, list properties and accounts. Always search tools first for current schemas.
- License 许可
- MIT
- 最近更新
- 2026-11-03
- Stars
- ★ 1
- Forks
- 0
01 前言 Front Matter
- name
- googleads-automation
- requires
- { "mcp": [ "rube" ] }
- description
- Automate Google Ads analytics tasks via Rube MCP (Composio): list Google Ads links, run GA4 reports, check compatibility, list properties and accounts. Always search tools first for current schemas.
03 SKILL.md 正文
Google Ads Automation via Rube MCP
Access Google Ads data through Google Analytics integration, run performance reports, list linked Ads accounts, and analyze campaign metrics using Rube MCP (Composio).
Toolkit docs: composio.dev/toolkits/googleads
Prerequisites
- Rube MCP must be connected (RUBE_SEARCH_TOOLS available)
- Active connection via
RUBE_MANAGE_CONNECTIONSwith toolkitgoogle_analytics - Always call
RUBE_SEARCH_TOOLSfirst to get current tool schemas
Setup
Get Rube MCP: Add https://rube.app/mcp as an MCP server in your client configuration. No API keys needed — just add the endpoint and it works.
- Verify Rube MCP is available by confirming
RUBE_SEARCH_TOOLSresponds - Call
RUBE_MANAGE_CONNECTIONSwith toolkitgoogle_analytics - If connection is not ACTIVE, follow the returned auth link to complete setup
- Confirm connection status shows ACTIVE before running any workflows
Note: Google Ads data is accessed through the Google Analytics toolkit integration. The tools below use GA4 properties linked to Google Ads accounts.
Core Workflows
1. List Google Ads Links for a Property
Use GOOGLE_ANALYTICS_ANALYTICS_ADMIN_PROPERTIES_GOOGLE_ADS to retrieve all Google Ads account links configured for a GA4 property.
Tool: GOOGLE_ANALYTICS_ANALYTICS_ADMIN_PROPERTIES_GOOGLE_ADS
Parameters:
- parent (required): Property resource name (format: "properties/{propertyId}")
- pageSize: Max results (1-200, default 50)
- pageToken: Pagination token
2. Run a GA4 Performance Report
Use GOOGLE_ANALYTICS_RUN_REPORT to run customized reports with dimensions, metrics, date ranges, and filters.
Tool: GOOGLE_ANALYTICS_RUN_REPORT
Parameters:
- property (required): Property resource (format: "properties/{property_id}")
- dimensions: Array of dimension objects (e.g., [{"name": "sessionCampaignName"}, {"name": "date"}])
- metrics: Array of metric objects (e.g., [{"name": "sessions"}, {"name": "totalRevenue"}])
- dateRanges: Array with startDate and endDate (e.g., [{"startDate": "2025-01-01", "endDate": "2025-01-31"}])
- dimensionFilter: Filter by dimension values
- metricFilter: Filter by metric values (applied after aggregation)
- orderBys: Sort results
- limit: Max rows to return (1-250000)
3. Check Dimension/Metric Compatibility
Use GOOGLE_ANALYTICS_CHECK_COMPATIBILITY to validate dimension and metric combinations before running a report.
Tool: GOOGLE_ANALYTICS_CHECK_COMPATIBILITY
Description: Validates compatibility of chosen dimensions or metrics
before running a report.
Note: Call RUBE_SEARCH_TOOLS to get the full schema for this tool.
4. List GA4 Accounts
Use GOOGLE_ANALYTICS_LIST_ACCOUNTS to enumerate all accessible Google Analytics accounts.
Tool: GOOGLE_ANALYTICS_LIST_ACCOUNTS
Parameters:
- pageSize: Max accounts to return
- pageToken: Pagination token
- showDeleted: Include soft-deleted accounts
5. List GA4 Properties Under an Account
Use GOOGLE_ANALYTICS_LIST_PROPERTIES to list properties for a specific GA4 account.
Tool: GOOGLE_ANALYTICS_LIST_PROPERTIES
Parameters:
- account (required): Account resource name (format: "accounts/{account_id}")
- pageSize: Max properties (1-200)
- pageToken: Pagination token
- showDeleted: Include trashed properties
6. Get Available Dimensions and Metrics
Use GOOGLE_ANALYTICS_GET_METADATA to discover all available fields for building reports.
Tool: GOOGLE_ANALYTICS_GET_METADATA
Description: Gets metadata for dimensions, metrics, and comparisons
for a GA4 property.
Note: Call RUBE_SEARCH_TOOLS to get the full schema for this tool.
Common Patterns
- Discover then report: Use
GOOGLE_ANALYTICS_LIST_ACCOUNTSto find account IDs, thenGOOGLE_ANALYTICS_LIST_PROPERTIESto find property IDs, thenGOOGLE_ANALYTICS_RUN_REPORTto pull data. - Validate before querying: Use
GOOGLE_ANALYTICS_CHECK_COMPATIBILITYto validate dimension/metric combinations before running reports to avoid 400 errors. - Campaign performance: Run reports with dimensions like
sessionCampaignName,sessionSource,sessionMediumand metrics likesessions,activeUsers,totalRevenue. - Ads link discovery: Use
GOOGLE_ANALYTICS_ANALYTICS_ADMIN_PROPERTIES_GOOGLE_ADSto find which Google Ads accounts are linked to each GA4 property. - Field discovery: Use
GOOGLE_ANALYTICS_GET_METADATAto list all available dimensions and metrics before constructing complex reports.
Known Pitfalls
- Dimension/metric compatibility: The GA4 API has strict compatibility rules. Not all dimensions can be combined with all metrics. Demographic dimensions (e.g.,
userAgeBracket,userGender) are often incompatible with session-scoped dimensions/filters (e.g.,sessionCampaignName,sessionSource). dateRangeis NOT a dimension: Do not includedateRangein the dimensions array. Usedate,dateHour,year,month, orweekinstead.exitsis NOT valid: Neitherexitsas a dimension nor as a metric is valid in GA4.- Property ID format: Must be
properties/{numeric_id}(e.g.,properties/123456789). Do not use Google Account IDs (long OAuth IDs). - Account ID format: Must be
accounts/{numeric_id}where the numeric ID is 6-10 digits. - Filter separation: Use
dimensionFilteronly for dimension fields andmetricFilteronly for metric fields. Mixing them will cause errors. - Max 9 dimensions and 10 metrics per report request.
Quick Reference
| Action | Tool | Key Parameters |
|---|---|---|
| List Ads links | GOOGLE_ANALYTICS_ANALYTICS_ADMIN_PROPERTIES_GOOGLE_ADS |
parent |
| Run report | GOOGLE_ANALYTICS_RUN_REPORT |
property, dimensions, metrics, dateRanges |
| Check compatibility | GOOGLE_ANALYTICS_CHECK_COMPATIBILITY |
(see full schema via RUBE_SEARCH_TOOLS) |
| List accounts | GOOGLE_ANALYTICS_LIST_ACCOUNTS |
pageSize |
| List properties | GOOGLE_ANALYTICS_LIST_PROPERTIES |
account, pageSize |
| Get metadata | GOOGLE_ANALYTICS_GET_METADATA |
(see full schema via RUBE_SEARCH_TOOLS) |
Powered by Composio
04 同仓库更多 Skills
x-article-draft-uploader
把本地 Markdown 转为经核验的 X Articles 新草稿。适用于需要保留首图封面、正文图片相对位置,并在独立 Playwright 会话中复用用户已授权 Chrome 登录态的任务;不负责公开发布。
wecom-operations
通过用户已配置的官方 wecom-cli 管理企业微信文档、智能文档、待办、会议和日程。适合创建或查询这些云端对象、把本地 Markdown 转为智能文档,以及在明确确认后更新或取消对象;不发送消息、不控制桌面客户端。
wecom-local-vault
Inspect authorized local WeCom databases on macOS, create private plaintext snapshots, and query or export contacts, conversations, and messages without modifying the source account store. Use when the user asks to parse 企业微信/WeCom local data, recover a private database snapshot, inspect local contacts or sessions, search chat history, or export a bounded conversation.
wechat-reading
Read and analyze WeRead/微信读书 search results, book metadata, bookshelf entries, progress, notes, highlights, public reviews, recommendations, and reading statistics through the official read-only Agent Gateway. Use for WeRead account questions or exports; do not imply that the current Gateway can add, remove, upload, rate, like, or edit content.
wechat-mp-batch-exporter
Build a bounded, private archive from known WeChat Official Account article URLs or an owner-authorized account-history export, with explicit reconciliation of article, publish-group, and platform-marked-original counts. Use for batch body capture, history normalization, or enhanced metrics/comments workflows. Do not use for a one-page summary or to automate the WeChat client.
wechat-local-vault
在 macOS 本机建立并查询私有微信数据快照。适用于盘点数据库、离线校验已有密钥候选、创建全量或增量明文快照、查会话与联系人、按时间检索消息、导出指定聊天、查看朋友圈或收藏,以及准备群聊摘要素材。所有查询只读,默认隐藏内部账号标识,不操控微信界面,也不发送任何内容。