GA4 SEO MCP
OCI · GHCR.IO/GERMANIU/GA4-SEO-MCP · 2 COMPONENTS
Set up and audit site measurement: GA4, Search Console and PageSpeed. Read-only unless enabled.
Available components
Last scanned (8 hours ago)
Scores higher than 68% of OCI servers
Category Marketing and SEO
How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →
Supply Chain Security0
- No malware scan is available for this kind of package: the supply-chain vendors we use do not cover it. This is a permanent gap in our coverage, not a finding about the package.Unverified
- Known CVEs could not be checked: this artifact ships no SBOM or dependency manifest, so there is no dependency list to read.Unverified
- Install-script risk not yet assessed.Unverified
- Dependency health could not be checked: this artifact ships no SBOM or dependency manifest, so there is no dependency list to read.Unverified
Provenance & Transparency48
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 12 days ago).Pass
- Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability76
- 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
- AI-judged instruction clarity (fair).Partial
- Tool/resource definitions use about 2358 tokens (~98/item across 24 items; 24 tools + 0 resources), lean.Pass
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management57
- Stability observed for 17 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage71
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 0% of tool parameters carry a description.Fail
- Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 24 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 25 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Unverified: 1 category
A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.
Checks we ran (12)
- Source repository
- Provenance
- License
- Maintenance
- Security disclosure
- Schema quality
- Stability
- Tool coverage
- Injection markers
- Destructive annotations
- Judged manipulation
- MCP protocol
Checks we could not complete (4)
These are gaps on our side, not findings about this package. We only credit what we can confirm, so a category made up entirely of them scores 0.
- Malware scan in Supply Chain Security (scores 0 for this)No malware scan is available for this kind of package: the supply-chain vendors we use do not cover it. This is a permanent gap in our coverage, not a finding about the package.
- Known CVEs in Supply Chain Security (scores 0 for this)Known CVEs could not be checked: this artifact ships no SBOM or dependency manifest, so there is no dependency list to read.
- Install scripts in Supply Chain Security (scores 0 for this)Install-script risk not yet assessed.
- Dependency health in Supply Chain Security (scores 0 for this)Dependency health could not be checked: this artifact ships no SBOM or dependency manifest, so there is no dependency list to read.
Does not apply to this package (2)
- Endpoint SecurityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
- Transport & ReachabilityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
The score does not measure everything. What the score does not measure →
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 5 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 53 to 57. That category is still filling its 30-day observation window: 16 days of observed history at the previous scan, 17 at this one. The score rises as the window fills, whether or not the server changes.
- 2 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 43 to 47. That category is still filling its 30-day observation window: 13 days of observed history at the previous scan, 14 at this one. The score rises as the window fills, whether or not the server changes.
- 31 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 37 to 40. That category is still filling its 30-day observation window: 11 days of observed history at the previous scan, 12 at this one. The score rises as the window fills, whether or not the server changes.
- 30 Oct 26 0
- Provenance: unverified → fail ▼ security
- 29 Oct 26 +1
- Provenance: fail → unverified ▼ security
- 27 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.
- 25 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.
- 24 Oct 26 0
- Package version: 0.1.0 → 0.1.2 functional
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 5 Nov 2026 · Analysed oci/ghcr.io/germaniu/ga4-seo-mcp@0.1.2
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | oci |
| Reason | No attestation published |
Background: How many MCP packages publish verified provenance →
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
audit_portfolio ~94
Summary metrics for several GA4 properties in one call. Returns sessions, active users, conversions, bounce rate and average session duration per property, plus the properties that failed and why. Args: property_ids: e.g. ['123456789', '987654321'].
| Name | Type | Req | Description |
|---|---|---|---|
| date_end | string | – | – |
| date_start | string | – | – |
| property_ids | array | yes | – |
Structured output declared, but exposes no named fields.
No examples provided.
bootstrap_site_measurement ~410
Plan, and optionally apply, the full measurement setup of a website. With apply=False (default) nothing is changed: it detects what already exists for the site (GA4 property and web stream matched by the site's domain, key events, custom dimensions, Search Console domain property) and returns the steps that would run. Show this plan to the user and get explicit confirmation before calling apply=True. With apply=True (requires the server to run with --enable-writes) it creates only the missing pieces, skipping what exists, so it is safe to re-run. It returns a step-by-step report with the GA4 measurement ID (G-...) and the DNS TXT token for Search Console. DNS verification and sitemap submission stay manual follow-up steps (sc_verify_site_dns, sc_submit_sitemap) because the TXT record must be published first. Args: site_url: the site, e.g. 'https://example.com'. account_id: GA4 account that owns (or will own) the property; see list_account_summaries. property_display_name: name for a new property; also used to find an existing one. time_zone: IANA time zone for a new property, e.g. 'America/Mexico_City'. currency_code: ISO 4217 currency for a new property, e.g. 'USD'. key_events: event names to mark as key events, e.g. ['generate_lead']. custom_dimensions: parameters to register as custom dimensions. apply: False = plan only (default); True = execute the plan.
| Name | Type | Req | Description |
|---|---|---|---|
| account_id | string | yes | – |
| apply | boolean | – | – |
| currency_code | string | yes | – |
| custom_dimensions | – | – | – |
| key_events | – | – | – |
| property_display_name | string | yes | – |
| site_url | string | yes | – |
| time_zone | string | yes | – |
Structured output declared, but exposes no named fields.
No examples provided.
conversions_summary ~49
Conversions and total users per event name: a summary of the active key events.
| Name | Type | Req | Description |
|---|---|---|---|
| date_end | string | – | – |
| date_start | string | – | – |
| property_id | string | yes | – |
Structured output declared, but exposes no named fields.
No examples provided.
events_summary ~70
Count of every event that fired, to audit what is actually being measured. Compare it with list_key_events to find key events that never fire.
| Name | Type | Req | Description |
|---|---|---|---|
| date_end | string | – | – |
| date_start | string | – | – |
| limit | integer | – | – |
| property_id | string | yes | – |
Structured output declared, but exposes no named fields.
No examples provided.
get_data_stream ~39
Get one data stream, including the measurement ID of a web stream.
| Name | Type | Req | Description |
|---|---|---|---|
| property_id | string | yes | – |
| stream_id | string | yes | – |
Structured output declared, but exposes no named fields.
No examples provided.
get_property ~35
Get the full settings of a GA4 property (time zone, currency, industry, type).
| Name | Type | Req | Description |
|---|---|---|---|
| property_id | string | yes | – |
Structured output declared, but exposes no named fields.
No examples provided.
list_account_summaries ~44
List every GA4 account you can access, with a summary of its properties. Start here to find the account_id and property_id the other tools need.
Input schema present but exposes no named parameters.
| Name | Type | Req | Description |
|---|---|---|---|
| result | array | yes | – |
No examples provided.
list_custom_dimensions ~32
List the custom dimensions declared on a GA4 property, with their scope.
| Name | Type | Req | Description |
|---|---|---|---|
| property_id | string | yes | – |
| Name | Type | Req | Description |
|---|---|---|---|
| result | array | yes | – |
No examples provided.
list_data_streams ~54
List the data streams (web, iOS, Android) of a GA4 property. Web streams include their measurement ID (G-XXXXXXX) and default URI.
| Name | Type | Req | Description |
|---|---|---|---|
| property_id | string | yes | – |
| Name | Type | Req | Description |
|---|---|---|---|
| result | array | yes | – |
No examples provided.
list_google_ads_links ~31
List the links between a GA4 property and Google Ads accounts.
| Name | Type | Req | Description |
|---|---|---|---|
| property_id | string | yes | – |
| Name | Type | Req | Description |
|---|---|---|---|
| result | array | yes | – |
No examples provided.
list_key_events ~32
List the key events (formerly conversions) declared on a GA4 property.
| Name | Type | Req | Description |
|---|---|---|---|
| property_id | string | yes | – |
| Name | Type | Req | Description |
|---|---|---|---|
| result | array | yes | – |
No examples provided.
list_properties ~72
List the GA4 properties under an account. Args: account_id: numeric account ID or 'accounts/123456789'. include_deleted: also return properties in the trash (soft-deleted, kept 35 days).
| Name | Type | Req | Description |
|---|---|---|---|
| account_id | string | yes | – |
| include_deleted | boolean | – | – |
| Name | Type | Req | Description |
|---|---|---|---|
| result | array | yes | – |
No examples provided.
psi_audit ~203
Run a PageSpeed Insights audit (Lighthouse lab test + CrUX field data) on a public URL. Takes 30-90 seconds. Without PAGESPEED_API_KEY the anonymous quota is small and Google may answer 429; set the key for regular use. Args: url: absolute public URL, e.g. 'https://example.com/'. strategy: 'mobile' (default) or 'desktop'. categories: subset of ['performance', 'accessibility', 'best-practices', 'seo']. Default: all four. Returns 0-100 category scores, lab Core Web Vitals (LCP, FCP, CLS, TBT, SI, TTFB) and, when Chrome has enough real-user traffic, CrUX p75 field data for the URL and its origin.
| Name | Type | Req | Description |
|---|---|---|---|
| categories | – | – | – |
| strategy | string | – | – |
| url | string | yes | – |
Structured output declared, but exposes no named fields.
No examples provided.
psi_field_data_only ~96
Only the CrUX field data (real Chrome users, p75 over 28 days) for a URL and its origin. PageSpeed Insights still runs a performance-only Lighthouse pass, so expect 15-40 seconds. `overall_category` is FAST, AVERAGE or SLOW; it is null when the page has too little traffic.
| Name | Type | Req | Description |
|---|---|---|---|
| strategy | string | – | – |
| url | string | yes | – |
Structured output declared, but exposes no named fields.
No examples provided.
run_realtime_report ~102
Realtime report for the last 30 minutes. Useful to confirm that a new event fires in production right after a deploy. Args: metrics: default ['activeUsers']; 'eventCount' also works. dimensions: default ['eventName']; also 'unifiedScreenName', 'country', 'deviceCategory'.
| Name | Type | Req | Description |
|---|---|---|---|
| dimensions | – | – | – |
| limit | integer | – | – |
| metrics | – | – | – |
| property_id | string | yes | – |
Structured output declared, but exposes no named fields.
No examples provided.
run_report ~268
Run a flexible GA4 report. Args: property_id: numeric ID or 'properties/123456789'. metrics: e.g. ['sessions', 'activeUsers', 'keyEvents']. Catalog: https://developers.google.com/analytics/devguides/reporting/data/v1/api-schema#metrics dimensions: optional, e.g. ['date', 'sessionSource', 'pagePath']. Catalog: https://developers.google.com/analytics/devguides/reporting/data/v1/api-schema#dimensions date_start: 'YYYY-MM-DD', 'today', 'yesterday' or 'NdaysAgo' (e.g. '28daysAgo'). date_end: same formats as date_start. limit: maximum rows (default 25). order_by_metric: sort by this metric, e.g. 'sessions'. order_desc: sort descending (default True). Returns the dimension and metric names, the date range, row_count and the rows.
| Name | Type | Req | Description |
|---|---|---|---|
| date_end | string | – | – |
| date_start | string | – | – |
| dimensions | – | – | – |
| limit | integer | – | – |
| metrics | array | yes | – |
| order_by_metric | – | – | – |
| order_desc | boolean | – | – |
| property_id | string | yes | – |
Structured output declared, but exposes no named fields.
No examples provided.
sc_list_sitemaps ~36
List the sitemaps submitted for a Search Console site, with errors and warnings.
| Name | Type | Req | Description |
|---|---|---|---|
| site_url | string | yes | – |
| Name | Type | Req | Description |
|---|---|---|---|
| result | array | yes | – |
No examples provided.
sc_list_sites ~77
List the Search Console sites you can access. Each entry has `siteUrl` ('sc-domain:example.com' for domain properties or a URL prefix like 'https://example.com/') and `permissionLevel` ('siteOwner', 'siteFullUser', 'siteRestrictedUser' or 'siteUnverifiedUser').
Input schema present but exposes no named parameters.
| Name | Type | Req | Description |
|---|---|---|---|
| result | array | yes | – |
No examples provided.
sc_page_performance ~58
Top pages in Google Search by clicks, with impressions, CTR (%) and average position.
| Name | Type | Req | Description |
|---|---|---|---|
| date_end | string | yes | – |
| date_start | string | yes | – |
| limit | integer | – | – |
| site_url | string | yes | – |
Structured output declared, but exposes no named fields.
No examples provided.
sc_query_breakdown_by_page ~76
Which search queries bring traffic to one specific page. Useful to decide which keywords to strengthen in that page's content.
| Name | Type | Req | Description |
|---|---|---|---|
| date_end | string | yes | – |
| date_start | string | yes | – |
| limit | integer | – | – |
| page_url | string | yes | – |
| site_url | string | yes | – |
Structured output declared, but exposes no named fields.
No examples provided.
sc_top_queries ~157
Top search queries with clicks, impressions, CTR (%) and average position. Args: site_url: 'sc-domain:example.com' or 'https://example.com/', exactly as in sc_list_sites. date_start: 'YYYY-MM-DD'. date_end: 'YYYY-MM-DD'. Search Console data lags 2-3 days. limit: rows to return (max 25000). country: optional ISO 3166-1 alpha-3 code to filter by, e.g. 'mex' or 'usa'.
| Name | Type | Req | Description |
|---|---|---|---|
| country | – | – | – |
| date_end | string | yes | – |
| date_start | string | yes | – |
| limit | integer | – | – |
| site_url | string | yes | – |
Structured output declared, but exposes no named fields.
No examples provided.
top_pages ~55
Top pages by sessions, with active users, bounce rate and average session duration.
| Name | Type | Req | Description |
|---|---|---|---|
| date_end | string | – | – |
| date_start | string | – | – |
| limit | integer | – | – |
| property_id | string | yes | – |
Structured output declared, but exposes no named fields.
No examples provided.
traffic_sources ~55
Top traffic sources (source / medium) with sessions, active users and conversions.
| Name | Type | Req | Description |
|---|---|---|---|
| date_end | string | – | – |
| date_start | string | – | – |
| limit | integer | – | – |
| property_id | string | yes | – |
Structured output declared, but exposes no named fields.
No examples provided.
web_vitals_summary ~98
Core Web Vitals reported by your own site as GA4 events. Requires the site to send web-vitals events with the parameters `web_vital_metric` and `web_vital_rating`, both registered as event-scoped custom dimensions. For Google's field data use psi_field_data_only instead.
| Name | Type | Req | Description |
|---|---|---|---|
| date_end | string | – | – |
| date_start | string | – | – |
| property_id | string | yes | – |
Structured output declared, but exposes no named fields.
No examples provided.
How do I install the GA4 SEO MCP server?
GA4 SEO MCP runs locally as a container image, launched with docker run --rm -i -e GOOGLE_APPLICATION_CREDENTIALS -e GA4SEO_TOOLSETS -e GA4SEO_ENABLE_WRITES -e PAGESPEED_API_KEY -e DATAFORSEO_LOGIN -e DATAFORSEO_PASSWORD -e GOOGLE_ADS_DEVELOPER_TOKEN -e GOOGLE_ADS_LOGIN_CUSTOMER_ID ghcr.io/germaniu/ga4-seo-mcp:0.1.2, plus the required --volume, which you supply. Ready-made configuration for Claude, Cursor, VS Code, Codex and 3 more is on this page, copied from each client's own documentation.
oci · ghcr.io/germaniu/ga4-seo-mcp
claude mcp add germaniu-ga4-seo-mcp -- docker run --rm -i -e GOOGLE_APPLICATION_CREDENTIALS -e GA4SEO_TOOLSETS -e GA4SEO_ENABLE_WRITES -e PAGESPEED_API_KEY -e DATAFORSEO_LOGIN -e DATAFORSEO_PASSWORD -e GOOGLE_ADS_DEVELOPER_TOKEN -e GOOGLE_ADS_LOGIN_CUSTOMER_ID ghcr.io/germaniu/ga4-seo-mcp:0.1.2
This image reads GOOGLE_APPLICATION_CREDENTIALS, GA4SEO_TOOLSETS, GA4SEO_ENABLE_WRITES, PAGESPEED_API_KEY, DATAFORSEO_LOGIN, DATAFORSEO_PASSWORD, GOOGLE_ADS_DEVELOPER_TOKEN and GOOGLE_ADS_LOGIN_CUSTOMER_ID. Set them in your client's env block for this server; docker run -e passes each one through to the container. Incomplete: the registry marks --volume as required and gives no value we can show, so it is not in this command. Add it before you run it.
What is the GA4 SEO MCP server?
GA4 SEO MCP is listed in the public MCP registry as io.github.GermaniU/ga4-seo-mcp. Set up and audit site measurement: GA4, Search Console and PageSpeed. Read-only unless enabled. This page covers its container image (ghcr.io/germaniu/ga4-seo-mcp).
Is the GA4 SEO MCP server safe to use?
GA4 SEO MCP scores 47 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the GA4 SEO MCP server expose?
GA4 SEO MCP exposes 24 tools: list_account_summaries, list_properties, get_property, list_data_streams, get_data_stream, and 19 more. Their descriptions and schemas cost roughly 2,243 tokens of context every time the server is loaded.
Is the GA4 SEO MCP server still maintained?
GA4 SEO MCP is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What licence is the GA4 SEO MCP server under?
GA4 SEO MCP declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.
What did VerifyMCP test on the GA4 SEO MCP server?
VerifyMCP ran 12 checks on GA4 SEO MCP, covering Source repository, Provenance, License, Maintenance and 8 more. 4 items could not be completed, a gap on our side rather than a finding about GA4 SEO MCP: Malware scan, Known CVEs, Install scripts and Dependency health. One category scores 0 for that reason, because we only credit what we can confirm. Endpoint Security and Transport & Reachability do not apply to a container image, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.