ga4_health_check
ga4 health check
Read-only GA4 health check. Verifies configured credentials, accessible properties, and metadata/property access without exposing OAuth tokens.
propertyId
com.getmcpads由 getmcpads.com 发布v2.1.2更新于 Nov 8, 2026
Google Analytics 4 MCP server: 27 read tools, no write tools.
只读的 Google Analytics 4 MCP 服务器,让助手运行 GA4 报表、透视表、漏斗与实时查询,并查看媒体资源设置。
Desktop only,通过 STDIO。 STDIO 服务会启动本地进程,因此需要 SourceWeft 桌面宿主。
参照 仓库 中的启动说明。
Explore traffic, conversions, funnels and property configuration through a read-only MCP server.
[Release] [CI] [Smithery] [License: Apache 2.0] [Node]
Watch the film · What's new · Install · Tool reference · Try hosted getmcpads
[Watch the getmcpads film: every ad account in one conversation with your AI assistant]
The film shows hosted getmcpads with sample data. Its MCP Apps, from creative galleries and alerts to Google Sheets exports and bulk launches, belong to the hosted product. This repository provides the standalone native API tools.
27 read tools · Read-only by design.
Run locally with your own platform credentials and a client that supports stdio MCP, such as Claude Desktop, Claude Code or Cursor. Your requests go directly to the platform. For managed connections, including supported ChatGPT setups, use the hosted option.
v2.1.1: Zod 4 security update · October 26, 2026
zod to 4.6.7. Every Zod release before 4.6.6 is covered by the high-severity advisory GHSA-mrhx-c7xc-m3w5: validating an oversized constrained collection can exhaust memory, and no Zod 3 release carries the fix. npm audit --omit=dev reports no vulnerability again.server-card.json is regenerated with Zod 4's JSON Schema output, which spells some constraints differently.Earlier releases
Source synchronization: SOURCE_SYNC.md.
Requires Node.js 22.23.4, 24.22.1 or 26.12.1, or a newer release of one of these lines. Older releases lack the October 2026 security fixes, and the server prints a warning on stderr when it starts on one. CI covers Node 22, 24 and 26.
This release makes no breaking change to the configuration. One change is announced for 3.0.0: GA4_PROPERTY_IDS is optional in 2.x and becomes required. When set, every tool is limited to the listed properties, and GA4_PROPERTY_ID must be one of them. When unset, the server starts as before and prints one line on stderr recommending it. The tools and their schemas are unchanged.
This is a GitHub source release. npm and MCP Registry versions are published separately. The commands below select this exact version; unpinned npx examples later in this document select the version currently available on npm.
Configure your MCP client to run node with the absolute path to dist/cli.js and the platform credentials documented below.
Prefer a managed connection? Use Google Analytics 4 with hosted getmcpads. Connect your account, select the data your assistant may access and use the hosted MCP connection. See the site for current features and plans.
GA4 rejects many metric and dimension combinations, and its errors rarely explain which pair
is at fault. This server carries the compatibility matrix, so ga4_check_compatibility and
ga4_validate_query let the model verify a combination before spending a call and a quota
token on it.
Quotas matter here more than on ad platforms: GA4 charges tokens per property per day, and a
few careless exploratory queries can exhaust them. ga4_get_property_quotas_snapshot shows
what is left.
There are no write tools, and no environment variable that adds any. Every tool calls a read method of the Data API or the Admin API.
This is not caution for its own sake. A misread report is a wrong answer you can spot. A mistaken write to an analytics property, a deleted audience or an edited data stream, corrupts the record you use to judge everything else, and often silently. The other servers we publish do have write tools, guarded by a mandatory preview. This one has none.
Our ad platform servers with guarded writes: Meta Ads · Google Ads · TikTok Ads
Analytics data is not anonymous by default. A GA4 property can carry a userId you set
yourself, a device identifier, or a Google Signals pseudonymous ID. An MCP conversation sends
whatever a tool returns to a model.
Identifiers are redacted by default wherever this server can return them, and showing them is an explicit opt-in, never the default.
Every one of these accepts includePersonalIdentifiers: true to return raw values, and
defaults to false.
Audience export rows are positional, so the redaction reads the export's dimension metadata to find identifier columns. If that metadata is missing, every value in the row is redacted rather than guessing which column is safe. Failing closed is the point.
Report rows are not redacted. ga4_run_report and the other reporting tools return what
you asked for. Altering the numbers a report returns would be worse than returning them.
So one decision stays yours: if your property carries a userId you consider personal, do not
request it as a report dimension in a conversation whose transcript leaves your machine.
Three values, obtained once.
In a Google Cloud project, enable the Google Analytics Data API and the Google Analytics Admin API, then create an OAuth client under APIs & Services → Credentials. Choose Desktop app for local use. Note the client ID and client secret.
Run the OAuth consent flow once, signed in as a Google account with access to your GA4
properties, and keep the refresh token. The analytics.readonly scope is enough, and it
is the only one you should grant.
📖 Google OAuth for installed apps
The refresh token does not expire. It is the sensitive value: anyone holding it can mint access tokens indefinitely. Use an OAuth client dedicated to this server so you can revoke it on its own.
Set GA4_PROPERTY_ID to avoid passing it on every call. Find it in GA4 under
Admin → Property Settings, or list them with ga4_list_properties.
Run ga4_health_check as your first call. It verifies the credentials and lists the
properties you can actually reach, without printing any secret.
~/Library/Application Support/Claude/claude_desktop_config.json (macOS)
or %APPDATA%\Claude\claude_desktop_config.json (Windows):
Restart Claude Desktop. Ask it: "list my Google Analytics properties".
.cursor/mcp.json in your project, same shape as the Claude Desktop config above.
Check your setup at any time:
Every tool is listed below. See server-card.json for complete parameter and output schemas.
invalid_grant, every
later call returns the same message with the steps to authorize again, and the server stops
asking Google for a token until it restarts.GA4_PROPERTY_IDS set, a call naming another property
is refused before any request, and discovery lists only the allowed properties.analyticsdata.googleapis.com,
analyticsadmin.googleapis.com and oauth2.googleapis.com. A test fails the build if a
fourth host appears in the source.redirect: "error", so a redirect
cannot forward a bearer token or client secret to another host. A test fails the build if
any fetch omits this.Full policy, including how personal data is handled: SECURITY.md.
Try hosted GA4 if you want to use this source without operating a local server. getmcpads also connects advertising, Search Console and GA4 through one MCP URL. Source availability and plan limits are listed on the site; connecting an account is still required.
See the current hosted tool catalogue and pricing before choosing a paid plan. This Apache 2.0 adapter remains independently useful with your own credentials.
Issues and pull requests are welcome. See CONTRIBUTING.md. Please read SECURITY.md before reporting anything security-related.
Apache License 2.0. See also NOTICE.
Google, Google Analytics and GA4 are trademarks of Google LLC. This project is not affiliated with, endorsed by, or sponsored by Google LLC. It is an independent client of a public API.
Every tool declares read/write annotations, parameter descriptions and a structured output schema. Successful calls expose the payload as structuredContent.result; errors retain isError: true. The generated server card contains definitions only.
Run npm run bundle -- /path/to/output to build a .mcpb desktop bundle from the current catalog. Credentials are entered locally during installation. This server remains read-only.
Meta Ads · Google Ads · Google Search Console · TikTok Ads · Pinterest Ads · X Ads
Maintained by Emmanuel at getmcpads. Questions: [email protected].
来源:README.md,提交 d66f3d7
ga4 health check
Read-only GA4 health check. Verifies configured credentials, accessible properties, and metadata/property access without exposing OAuth tokens.
propertyIdga4 list properties
List all GA4 properties accessible with the current credentials. Returns property ID, display name, timezone, and currency.
无需输入参数。
ga4 run report
Run a GA4 analytics report with intelligent query planning. Supports 52 metrics, 63 dimensions, auto-pagination. Use ga4://metrics and ga4://dimensions resources for available fields. Max 9 dimensions + 10 metrics per request.
limitoffsetendDatemetrics必填orderBystartDatedatePresetdimensionspropertyId必填autoPaginateorderDirectionga4 run realtime report
Run a read-only GA4 Data API realtime report. Realtime supports only a limited subset of dimensions and metrics.
limitmetricsorderBysdimensionspropertyId必填metricFilterminuteRangeskeepEmptyRowsdimensionFilterga4 get metadata
Get the complete list of dimensions and metrics available for a specific GA4 property. Useful for discovering custom dimensions/metrics.
propertyId必填ga4 get custom definitions
List custom dimensions and custom metrics exposed by GA4 Data API metadata. Read-only fallback for custom definition inventory.
propertyId必填ga4 get key events
Inventory GA4 key events/conversions using metadata-aware Data API reports. Returns best-effort event names and counts.
limitendDatestartDatedatePresetpropertyId必填ga4 get ecommerce diagnostics
Read-only ecommerce coverage diagnostics for core ecommerce events, revenue metrics, and item-level reporting over a date range.
limitendDatestartDatedatePresetpropertyId必填ga4 get event parameters
Best-effort event parameter inventory from GA4 metadata plus event reports. Documents Data API limitations for raw parameters.
limitendDatestartDatedatePreseteventNamespropertyId必填ga4 run funnel recipe
Run a read-only configurable funnel recipe using one GA4 report per eventName/pagePath step and return simple step counts.
steps必填metricendDatestartDatedatePresetpropertyId必填ga4 get audience export diagnostics
Read-only Audience Export diagnostics. Lists existing audience exports, state counts, and optionally samples rows from an existing export.
pageSizepropertyId必填sampleLimitincludeRowSampleaudienceExportNameincludePersonalIdentifiersga4 get audience diagnostics
Read-only audience diagnostics from Admin API audiences, Data API recurring audience lists, and observed audienceName report fallback.
limitendDatestartDatedatePresetpropertyId必填includeDefinitionsrecurringAudienceListNamega4 get bigquery export diagnostics
Detect GA4 BigQuery export links and diagnose export modes, stream coverage, excluded events, and dataset location.
propertyId必填includeDataStreamsga4 get server side tagging diagnostics
Best-effort read-only server-side tagging diagnostics from data streams, Measurement Protocol secrets, event rules, and stream settings.
propertyId必填includeRulesincludeSettingsga4 run advanced funnel report
Run the GA4 Data API v1alpha runFunnelReport endpoint with optional breakdown/next-action, falling back to read-only step counts if unavailable.
limitsteps必填endDatestartDatedatePresetpropertyId必填isOpenFunnelbreakdownLimitnextActionLimitvisualizationTypebreakdownDimensionnextActionDimension另有 1 个ga4 get channel groups
List custom channel groups defined for a GA4 property.
propertyId必填ga4 validate query
Validate a metric/dimension combination BEFORE executing. Checks max limits (9 dims, 10 metrics), ecommerce rules, and dimension compatibility.
metrics必填dimensionsga4 run pivot report
Run a read-only GA4 Data API pivot report with native filters, ordering, quota state, multiple date ranges, and up to 250,000 pivot cells. Every pivot requires an explicit limit.
report必填propertyId必填ga4 batch run reports
Run 1-5 independent read-only GA4 Core reports for the same property in one official Data API batch request.
reports必填propertyId必填ga4 batch run pivot reports
Run 1-5 independent read-only GA4 pivot reports for the same property in one official Data API batch request.
reports必填propertyId必填ga4 check compatibility
Ask the official GA4 Data API which dimensions and metrics are compatible with a proposed Core report selection.
metricsdimensionspropertyId必填metricFilterdimensionFiltercompatibilityFilterga4 get property quotas snapshot
Read the current GA4 Data API property quota snapshot from the official v1alpha endpoint. This does not run a report, but Google still charges one property-quota token to the category with the most remaining quota.
propertyId必填ga4 list accounts
List raw GA4 Analytics Admin accounts accessible to the authenticated user (read-only, auto-paginated).
pageSizega4 list admin resources
List an allowlisted GA4 Admin collection in read-only mode: streams, custom definitions, key events, audiences, product links, annotations, channel groups, expanded datasets, subproperty/rollup configuration, and access bindings.
pageSizecollection必填propertyId必填includePersonalIdentifiersga4 get property configuration
Read GA4 property details plus selected singleton Admin settings (attribution, retention, Google Signals, reporting identity, or user-provided-data settings).
settingspropertyId必填ga4 list audience exports
List existing GA4 Audience Export snapshots and Recurring Audience Lists without creating new exports.
pageSizepropertyId必填includeRecurringga4 query audience export
Query rows from an existing GA4 Audience Export. User/device identifiers are redacted by default; include them only through explicit opt-in.
limitoffsetaudienceExportName必填includePersonalIdentifiers已满足适用检查项的 90%
该评分衡量此收录条目的完整程度,依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价,也不表示服务器安全或当前可用:可连通性是带日期的检查结果,评分也不包含安装量或用户评价。
请在注册中心条目中声明凭据请求头,或保持端点能够响应探测,以便判定其认证方式。
git clone --branch v2.1.1 --depth 1 https://github.com/get-mcp-ads/google-analytics-mcp-server.gitcd google-analytics-mcp-servernpm cinpm run build{ "mcpServers": { "google-analytics": { "command": "npx", "args": ["-y", "@getmcpads/google-analytics-mcp-server"], "env": { "GA4_CLIENT_ID": "your-client-id", "GA4_CLIENT_SECRET": "your-client-secret", "GA4_REFRESH_TOKEN": "your-refresh-token", "GA4_PROPERTY_IDS": "123456789" } } }}claude mcp add google-analytics --env GA4_CLIENT_ID=... --env GA4_CLIENT_SECRET=... --env GA4_REFRESH_TOKEN=... -- npx -y @getmcpads/google-analytics-mcp-servergit clone https://github.com/get-mcp-ads/google-analytics-mcp-server.gitcd google-analytics-mcp-servernpm install && npm run buildcp .env.example .env # then fill in your credentialsnpm startnpm run doctor