跳过安装。2 分钟内即可运行。
在 cloud.anythingmcp.com 开始免费试用，一键添加 Matomo，然后将你的 AI 客户端（Claude、ChatGPT、Copilot 或 Cursor）指向生成的 MCP 端点。无需 Docker，无需 git clone，无需任何工程经验。
Summary
Matomo web analytics: visits, page and entry-page reports, referrers, countries and devices, goal conversions and live visitor detail. Reporting API on Matomo Cloud or your own instance, token_auth.
试试这样问
Matomo 的示例提示
点击任意提示即可复制，然后粘贴到 Claude、ChatGPT、Cursor、Gemini、Copilot 或 OpenClaw 中，在该连接器上运行。
Claude 是 AI，可能会出错。请核对回答。
💡 无需安装? 直接使用 cloud.anythingmcp.com。 登录、点击 Connectors → Matomo、粘贴凭证、生成 MCP API key — 完成。无 Docker、无
git clone、无本地服务器。
Matomo + Gemini
Matomo web analytics: visits, page and entry-page reports, referrers, countries and devices, goal conversions and live visitor detail. Reporting API on Matomo Cloud or your own instance, token_auth.
前提条件
完整的设置说明已内置在连接器中 (在 store 中选择连接器时可见)。所需环境变量:
MATOMO_URL, MATOMO_TOKEN
步骤 1 — 获取凭证
Getting a token
- Sign in to Matomo and open Administration → Personal → Security → Auth tokens, then Create new token.
- Leave 'Only allow secure requests' unticked only if you must — with it ticked, Matomo 4+ requires the token in a POST body rather than a query parameter. This adapter sends it as a query parameter (GET), which is Matomo's classic Reporting API shape and what the majority of installs accept.
- Set
MATOMO_URLto your Matomo root (no trailing slash, no/index.php) andMATOMO_TOKENto the token.
…(continued in the in-app connector instructions)
步骤 2 — 安装 adapter
curl -fsSL https://raw.githubusercontent.com/HelpCode-ai/anythingmcp/main/docker-compose.quickstart.yml -o docker-compose.yml
printf 'JWT_SECRET=%s\nENCRYPTION_KEY=%s\n' "$(openssl rand -hex 32)" "$(openssl rand -hex 32)" > .env
docker compose up -d
步骤 3 — 在 Gemini 中添加连接器
Gemini CLI 从 ~/.gemini/settings.json (Windows: %APPDATA%\gemini\settings.json) 读取 MCP 服务器。添加:
{
"mcpServers": {
"anythingmcp": {
"httpUrl": "https://cloud.anythingmcp.com/mcp",
"headers": { "Authorization": "Bearer YOUR_MCP_API_KEY" }
}
}
}
- 从 AnythingMCP 获取你的 MCP API key。
- 保存文件并重启
gemini。 - 在 Gemini CLI 中运行
/mcp—Matomo应显示为可用。 - Vertex AI Studio: 将
https://cloud.anythingmcp.com/mcp传入请求的tools数组,使用相同的 Bearer 头。
可用工具
| Tool | What it does |
|---|---|
matomo_get_version | Read the Matomo version of this instance |
matomo_list_sites | List the sites this token can report on, with their id, name, main URL, timezone and currency |
matomo_get_visits_summary | Read the headline numbers for a period: visits, unique visitors, actions, bounce rate, average visit duration and actions per visit |
matomo_get_page_urls | Read the page report: which URLs were viewed, how often, their average time on page, bounce rate and exit rate |
matomo_get_entry_pages | Read which pages visitors arrived on, with entries, bounce rate and the visits that followed — the landing-page view, not the pageview vie |
matomo_get_referrers | Read where the traffic came from: search engines, websites, social networks, campaigns and direct entry, with visits and actions for each |
matomo_get_countries | Read the visits broken down by country, with visit counts, actions and bounce rate — the geography of the audience |
matomo_get_device_types | Read the visits broken down by device type — desktop, smartphone, tablet — with visits, actions and bounce rate |
matomo_get_goals | Read goal conversions for a period: conversions, conversion rate and revenue, overall or for one goal |
matomo_get_last_visits | Read individual recent visits with their referrer, country, device, and the pages each one viewed in order |
FAQ
Gemini 1.5 Pro 或 2.x 支持 MCP 吗? 支持 — Gemini CLI ≥ 0.4 与 Vertex AI tools API 均接受带 Bearer 头的 MCP httpUrl 连接器。
下一步
这份指南对你有帮助吗?
