Allows running reports, viewing top pages, analyzing traffic sources, checking realtime users, and comparing periods using the Google Analytics 4 Data API.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@GA4 MCP Server What are my top pages this month?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
A Model Context Protocol (MCP) server that connects Claude Desktop (and other MCP clients) to the Google Analytics 4 Data API — run reports, view top pages, analyze traffic sources, check realtime users, and compare periods.
Tool | Description |
| List all GA4 properties accessible by the service account |
| Run a custom report with any dimensions and metrics |
| Top pages by sessions with bounce rate and duration |
| Traffic breakdown by source/medium |
| Conversion events and their counts |
| Realtime active users and top pages |
| Compare current vs previous period with percentage changes |
Token-bucket rate limiter — respects GA4's 10 concurrent request limit
Auto-retry on 429/5xx — exponential backoff (2s, 4s, 8s) up to 3 retries
Lazy imports — defers heavy Google client libraries for fast MCP handshake
Actionable error messages — guides users to fix permission, auth, and input errors
Related MCP server: Google Analytics MCP Server
Python 3.11+
A Google Cloud service account with GA4 access
Claude Desktop (or any MCP-compatible client)
Create a Google Cloud service account
Enable the Google Analytics Data API and Google Analytics Admin API in your project
Download the service account JSON key file
In GA4: go to Admin > Property Access Management and add the service account email as a Viewer
Run the published package without a global install:
uvx --from luminarylane-ga4-mcp luminarylane-ga4-mcpThe package is published on PyPI. Alternatively, install it with pip install luminarylane-ga4-mcp.
Claude Desktop (claude_desktop_config.json):
{
"mcpServers": {
"ga4": {
"command": "uvx",
"args": ["--from", "luminarylane-ga4-mcp", "luminarylane-ga4-mcp"],
"env": {
"GA4_CREDENTIALS_PATH": "/path/to/service_account_credentials.json",
"GA4_PROPERTY_ID": "123456789"
}
}
}
}Environment variables:
Variable | Required | Description |
| Yes | Path to service account JSON key file |
| No | Default property ID (can also pass per-tool) |
For local development only, credential files may be stored in paths excluded by .gitignore; never commit them. Prefer the explicit environment-variable path above.
Once configured, ask Claude to:
"What are my top pages this month?"
"Show me traffic sources for the last 7 days"
"How does this week compare to last week?"
"Are there any active users on the site right now?"
"Run a report on sessions by country for the last 90 days"
"What conversion events fired this week?"
"List all GA4 properties I have access to"
GA4 Data API allows 10 concurrent requests per property. The server handles this with a client-side token bucket and exponential backoff retries.
The service account doesn't have access to the GA4 property. Go to GA4 Admin > Property Access Management and add the service account email as a Viewer.
Property IDs are numeric (e.g., 123456789), not the measurement ID (G-XXXXXXX). Use ga4_list_properties to find valid IDs.
Check that GA4_CREDENTIALS_PATH points to a valid service account JSON key file.
Check the GA4 Dimensions & Metrics Explorer for valid names. Common mistakes: sessions not session, sessionSource not source, pagePath not page.
See CONTRIBUTING.md. Never commit service-account credentials or OAuth tokens.
Report vulnerabilities privately using GitHub's private vulnerability reporting; do not include credentials in public issues.
MIT License — see LICENSE for details.
Anthropic for the MCP specification
Google Analytics Data API for the reporting API
Compare current period vs previous period for key metrics. Shows absolute values and percentage change for each metric.
Args: property_id: GA4 property ID (numeric). Leave empty to use GA4_PROPERTY_ID env var. metrics: Comma-separated metrics to compare (default: sessions, users, pageviews, bounce rate, avg session duration, conversions). days: Period length in days (default: 28). Compares last N days vs the N days before that.
| Name | Required | Description | Default |
|---|---|---|---|
| days | No | ||
| metrics | No | sessions,totalUsers,screenPageViews,bounceRate,averageSessionDuration,conversions | |
| property_id | No |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the burden of behavioral disclosure. It explains the comparison logic, the period length default, and the env var fallback for property_id. It doesn't mention edge cases like timezone handling or empty property_id behavior, but the core behavior is well disclosed.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise, front-loaded with the core purpose, and uses a clear Args block. Every sentence provides useful information without redundancy. It is well-structured for quick comprehension.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool has three parameters, no annotations, but an output schema exists. The description covers the main behavior and all parameters, and given the output schema, no further detail on return values is necessary. It is complete enough for an agent to invoke the tool correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, so the description must fully document parameters. It does this excellently: property_id is numeric with an env var fallback, metrics is comma-separated with a default list, and days is explained with the 'last N vs N before' logic. This adds significant meaning beyond the raw schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a specific verb and resource: 'Compare current period vs previous period for key metrics.' It clearly differentiates from sibling tools like ga4_get_report or ga4_get_realtime by focusing on period-over-period comparison rather than single-period reports or realtime data.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The intended use case is clear: comparing current and previous periods with a configurable period length. It explains the period logic ('last N days vs the N days before that') and provides defaults. It does not explicitly state when not to use it or mention alternatives, but the context is clear enough for an agent to select it appropriately.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get conversion events and their counts. Shows which events are firing and how often, broken down by event name.
Args: property_id: GA4 property ID (numeric). Leave empty to use GA4_PROPERTY_ID env var. days: Lookback period in days (default: 28). row_limit: Max rows to return (default: 20).
| Name | Required | Description | Default |
|---|---|---|---|
| days | No | ||
| row_limit | No | ||
| property_id | No |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description is the only source of behavioral info. It clearly describes the output (counts, event names) and the default lookback period, and explains that property_id can fall back to an environment variable. It does not mention any side effects, rate limits, or required permissions, but for a read-oriented tool this description is reasonably transparent.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise and well-structured: a one-sentence summary, a brief explanation, and a clear Args list. Every sentence adds value, and the format makes it easy to parse.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool is simple with three parameters, and the description covers its purpose, output, and parameter semantics. The output schema exists so return format isn't needed. The only gap is the lack of explicit mention of required permissions or usage context relative to siblings, but this is not critical for invocation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The Args section explains each parameter's meaning (property_id with env var fallback, days as lookback, row_limit as max rows) and provides defaults. This goes well beyond the input schema, which only lists types and defaults, and provides valuable context for correct invocation.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's function: 'Get conversion events and their counts' and explains the breakdown by event name. This specific verb and resource clearly distinguishes it from sibling tools like ga4_get_top_pages or ga4_get_traffic_sources.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies the tool should be used when conversion event data is needed, but it does not explicitly state when to use this versus alternatives. There is no mention of exclusions or comparisons to sibling tools, so the agent must infer usage from the tool's name and description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get realtime active users and current events on the site. Shows what's happening RIGHT NOW — active users, top pages, traffic sources.
Args: property_id: GA4 property ID (numeric). Leave empty to use GA4_PROPERTY_ID env var.
| Name | Required | Description | Default |
|---|---|---|---|
| property_id | No |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. It states what the tool returns (active users, top pages, traffic sources) but doesn't mention that it's a read-only operation, any authentication requirements, or potential rate limits. The only extra behavioral detail is the env var fallback for property_id, which is helpful but not sufficient for full transparency. The description leans heavily on the tool's obvious read-only nature without explicitly stating it.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely concise: two sentences plus an Args section. The main purpose is front-loaded in the first sentence, and the second sentence adds valuable detail about what the tool shows. The Args section is clean and directly relevant. No fluff or redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool is simple, has only one parameter well documented, and an output schema exists (so return values need not be explained). The description covers the core functionality and purpose. It could potentially mention prerequisites or that it's read-only, but given the low complexity and existing output schema, the description is sufficiently complete for practical use.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, so the description must compensate. It fully explains the single parameter: property_id is a numeric GA4 property ID, and leaving it empty uses the GA4_PROPERTY_ID environment variable. This adds significant meaning beyond the schema's bare 'string type, default empty' and completely addresses parameter semantics.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the specific action ('Get realtime active users and current events') and resource (the site's real-time data). It provides a clear sense of what the tool does without needing to infer. However, it does not explicitly distinguish this from sibling tools like ga4_get_top_pages or ga4_get_traffic_sources, which might overlap in scope, so it doesn't earn a 5.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description gives clear context for when to use this tool: it shows what's happening 'RIGHT NOW', implying real-time monitoring. It doesn't explicitly mention alternatives or exclusions, but the 'right now' phrasing effectively communicates the intended use case. This meets the 'clear context, no exclusions' level.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Run a custom GA4 report with any combination of dimensions and metrics.
Args: property_id: GA4 property ID (numeric). Leave empty to use GA4_PROPERTY_ID env var. dimensions: Comma-separated dimension names (e.g., "date", "sessionSource,sessionMedium", "pagePath", "country", "deviceCategory"). Default: "date". metrics: Comma-separated metric names (e.g., "sessions,totalUsers,screenPageViews", "bounceRate,averageSessionDuration,conversions"). Default: "sessions,totalUsers,screenPageViews". days: Lookback period in days (default: 28). row_limit: Max rows to return (default: 20, max: 100).
| Name | Required | Description | Default |
|---|---|---|---|
| days | No | ||
| metrics | No | sessions,totalUsers,screenPageViews | |
| row_limit | No | ||
| dimensions | No | date | |
| property_id | No |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It explains the tool executes a report and details parameter behavior, defaults, and row limit maximum. It does not mention rate limits or handling of invalid dimension/metric names, but the output schema covers return structure, and the read-only nature is self-evident.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is well-structured with an 'Args' block, clear parameter explanations, and useful examples. Every sentence adds value, and the format is scannable and efficient.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool has an output schema, so return values need no further explanation. The description fully covers parameters, defaults, limits, and the custom-report use case, making it complete for the tool's complexity and context.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, so the description must compensate, and it does excellently. It explains every parameter with examples, defaults, and constraints (e.g., 'row_limit max: 100'), adding meaning far beyond the bare schema definitions.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states a specific verb ('Run') and resource ('custom GA4 report') with the ability to combine dimensions and metrics. It distinguishes itself from specialized sibling tools by emphasizing 'any combination' of dimensions and metrics.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies this is for arbitrary/custom report needs versus the specialized siblings (e.g., top pages, traffic sources, conversions), but it does not explicitly state when to prefer this tool over a sibling. The 'custom' framing makes the use case clear enough.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get top pages by sessions. Shows page path, sessions, users, pageviews, bounce rate, and average session duration.
Args: property_id: GA4 property ID (numeric). Leave empty to use GA4_PROPERTY_ID env var. days: Lookback period in days (default: 28). row_limit: Max rows to return (default: 20).
| Name | Required | Description | Default |
|---|---|---|---|
| days | No | ||
| row_limit | No | ||
| property_id | No |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the transparency burden. It adds useful behavioral detail by explaining the property_id env var fallback and implying a read-only report via 'Get'. However, it omits potential rate limits, authentication requirements, or data freshness considerations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise and well-structured: a clear purpose sentence followed by a bulleted list of arguments. Every sentence contributes value, with no redundancy or filler.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given that an output schema exists and parameters are well documented, the description is nearly complete for a simple reporting tool. Minor gaps include not mentioning authentication prerequisites or potential caveats like data lag, but these are not critical for basic usage.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema provides only types and defaults, but the description fully compensates by giving meaning to each parameter: property_id (numeric GA4 ID with env var fallback), days (lookback period), and row_limit (max rows). This is exactly what is needed when schema description coverage is 0%.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool retrieves top pages ranked by sessions and enumerates the specific metrics returned (page path, sessions, users, etc.). This makes its function unambiguous and distinguishes it from sibling tools like ga4_get_traffic_sources or ga4_get_conversions.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
There is no explicit guidance on when to use this tool versus alternatives. The description only explains what it does and its parameters, leaving usage context implied rather than providing clear selection criteria or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get traffic sources breakdown by source/medium. Shows sessions, users, bounce rate, and conversions per traffic source.
Args: property_id: GA4 property ID (numeric). Leave empty to use GA4_PROPERTY_ID env var. days: Lookback period in days (default: 28). row_limit: Max rows to return (default: 20).
| Name | Required | Description | Default |
|---|---|---|---|
| days | No | ||
| row_limit | No | ||
| property_id | No |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden. It indicates a 'get' operation, implying read-only, but does not disclose potential behavioral traits such as sorting order, pagination, rate limits, or data freshness. The env var fallback for property_id is a useful detail, but otherwise the behavior is only partially transparent.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely concise, starting with the main purpose in one sentence, then listing parameters in a clear arg block. Every sentence earns its place with no filler.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the presence of an output schema, the description need not explain return values. It covers the core functionality, metrics, and parameters adequately for a straightforward retrieval tool. However, it lacks explicit guidance on usage context or alternatives, which would make it more complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 0% description coverage, so the description adds essential meaning for all three parameters. It explains that property_id can use an env var default, days is a lookback period, and row_limit caps results. This goes beyond the schema but could provide more detail on value ranges or formats.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it retrieves traffic sources breakdown by source/medium and lists the specific metrics (sessions, users, bounce rate, conversions). This specific verb+resource combination distinguishes it from sibling tools like ga4_get_top_pages and ga4_get_conversions.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies use for traffic source analysis but does not explicitly mention when to choose this over alternatives. No exclusions or alternative tool names are given, leaving the agent to infer from the name and sibling context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List all GA4 properties accessible by the service account. Returns property IDs and display names.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of transparency. It discloses that the operation lists properties and returns IDs/names, implying a read-only action, but it does not state safety traits, error implications, or limitations. The mention of service account scope adds useful context, but there is no explicit statement about non-mutating behavior.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two short sentences that immediately state the action and output. There is no redundant or filler content, making it highly concise and well-structured.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity (no parameters) and the presence of an output schema, the description is mostly complete. It covers the key purpose and return items. However, it does not mention typical edge cases like empty results or auth failures, nor does it relate itself to sibling tools. For such a simple tool, this is adequate, hence a 4.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
There are zero parameters, so the schema provides no semantics to clarify. Per the rubric, a baseline of 4 is appropriate for parameterless tools. The description does not need to explain parameters and adds nothing beyond the schema, which is acceptable in this case.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'List' and the resource 'all GA4 properties', which immediately establishes the tool's function. It also specifies the return content (property IDs and display names), distinguishing it from sibling tools that focus on reports, pages, or traffic sources.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description gives no explicit guidance on when to use this tool versus alternatives. It implies a listing/discovery use case, and the scope 'accessible by the service account' gives some context, but it does not mention that this might be a prerequisite for other GA4 tools or when to prefer it over siblings.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v1.0.1ga4_compare_periodsga4_get_conversionsga4_get_realtimega4_get_reportga4_get_top_pagesga4_get_traffic_sourcesga4_list_propertiesScored across 7 tools
Each special-purpose tool targets a distinct analytical view (top pages, traffic sources, conversions, realtime, period comparison), and ga4_get_report is explicitly generic. While ga4_get_report could theoretically replicate the specialized tools, its purpose is clearly different, so confusion is unlikely.
All tools follow the consistent ga4_<verb>_<noun> pattern with lowercase and underscores. Verbs are list, get, and compare, which is a predictable and uniform convention across the set.
With 7 tools, the server is well-scoped for a GA4 analytics wrapper. It covers property discovery and the most common report types without unnecessary bloat or excessive minimalism.
The tool set covers property listing, common report dimensions, custom queries, realtime data, and period-over-period comparison. Advanced GA4 features like funnel analysis or user exploration are absent, but these are beyond the typical expectation for an analytics MCP server.
Connect Google Analytics to ChatGPT. Query GA4 data in plain English and get instant insights.
GA4, Google Ads and Search Console in Claude. Read-only OAuth, multi-account for agencies.
Read and edit GA4, Search Console and Google Tag Manager from any MCP client. 29 tools.
GA4 conversion analyst inside Claude — funnel drops, traffic anomalies, device gaps, with numbers.
