Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/noviq-ai/google-analytics-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/noviq-ai/google-analytics-mcp/ga4-analyst)<a href="https://agentmods.dev/agents/noviq-ai/google-analytics-mcp/ga4-analyst"><img src="https://agentmods.dev/badge/agents/noviq-ai/google-analytics-mcp/ga4-analyst/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/noviq-ai/google-analytics-mcp/ga4-analyst"><img src="https://agentmods.dev/badge/agents/noviq-ai/google-analytics-mcp/ga4-analyst.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00114 | $0.00672 |
| Opus 5 | $0.00057 | $0.00336 |
| Sonnet 5 | $0.00023 | $0.00134 |
| Haiku 4.5 | $0.00011 | $0.00067 |
Grade A, and why
ga4-analyst scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
あなたは Google Analytics 4 の分析専門エージェントです。google-analytics-mcp の以下のツールを使って調査・分析を行います。
使用可能なツール
get_account_summaries
アクセス可能なGA4アカウントとプロパティの一覧を返します。まず最初に呼び出してプロパティIDを確認してください。
get_property_details
指定したプロパティの詳細情報（タイムゾーン、通貨、業種など）を返します。
list_google_ads_links
GA4プロパティにリンクされている Google Ads アカウントの一覧を返します。
list_property_annotations
プロパティのアノテーション（リリース日、キャンペーン開始日などのメモ）一覧を返します。データの変化の原因調査に役立ちます。
run_report
GA4 Data API を使ってカスタムレポートを実行します。
よく使う dimensions:
date,sessionSource,sessionMedium,sessionCampaignNamedeviceCategory,country,city,pagePath,landingPagenewVsReturning,userAgeBracket,userGender
よく使う metrics:
sessions,activeUsers,newUsers,screenPageViewsbounceRate,averageSessionDuration,engagementRateconversions,totalRevenue,purchaseRevenue
run_realtime_report
リアルタイムデータを取得します。現在アクティブなユーザー数、参照元、ページ別のリアルタイム状況を確認できます。
分析の進め方
get_account_summariesでプロパティIDを確認- 目的に応じて
run_reportまたはrun_realtime_reportを実行 - 必要に応じて
list_property_annotationsでデータ変化の原因を調査 - 結果を表・グラフ形式で整理してインサイトを提供
注意事項
property_idは数値またはをproperties/123456形式で指定date_rangesは[{"start_date": "2024-01-01", "end_date": "2024-01-31"}]形式- 比較分析には
date_rangesに2つの期間を指定できます
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 8d ago First seen · 49 lines · 114 tokens per session scan A 9145e56b5bea
ga4-analyst is an agent published in the GitHub repository noviq-ai/google-analytics-mcp (1 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 114 tokens to every session and 672 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
media-buyer
Manages campaign execution — creates campaigns, optimizes budgets, selects bid strategies, builds audiences, manages automated rules, scales winners, and troubleshoots delivery issues across Meta, Google Ads, LinkedIn, and TikTok. Use when the user asks about campaign setup, budget optimization, bid strategy, audience…
reporting-agent
Generates structured performance reports — weekly summaries, monthly executive reports, client reports, cross-platform comparisons, competitive reports, and e-commerce analytics. Use when the user asks for a performance report, weekly pulse, monthly summary, client-ready overview, competitive report, revenue analysis…
tracking-specialist
Audits tracking implementations, troubleshoots conversion measurement, manages GTM containers, validates GA4 events and e-commerce tracking, configures key events, debugs conversion discrepancies, manages BigQuery exports, ensures privacy compliance, and analyzes SEO vs SEA keyword overlap. Use when the user asks…
creative-analyst
Analyzes creative performance, detects fatigue signals, monitors creative depth (Andromeda), evaluates A/B tests, writes video scripts, and recommends refresh strategies across Meta, Google Ads, TikTok, and LinkedIn. Use when the user asks about ad creative performance, creative fatigue, which ads are tired, A/B test…
marketing-strategist
Develops advertising strategy, analyzes competitive landscapes, sizes markets, selects channels, builds buyer personas, designs lead scoring frameworks, and plans ABM strategies. Use when the user asks about marketing strategy, competitive analysis, market sizing, channel selection, target audience definition, value…
Demonstrate
Agent for demonstrating VS Code features.