Installation überspringen. In unter 2 Minuten einsatzbereit.
Starte eine kostenlose Testphase auf cloud.anythingmcp.com, füge Matomo mit einem Klick hinzu und richte deinen KI-Client (Claude, ChatGPT, Copilot oder Cursor) auf den erzeugten MCP-Endpoint. Kein Docker, kein git clone, keinerlei Entwicklungserfahrung nötig.
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.
Frag einfach
Beispiel-Prompts für Matomo
Klick auf einen Prompt, um ihn zu kopieren. In Claude, ChatGPT, Cursor, Gemini, Copilot oder OpenClaw einfügen — und gegen diesen Connector laufen lassen.
Claude ist KI und kann Fehler machen. Bitte Antworten gegenprüfen.
💡 Keine Installation? Nutze cloud.anythingmcp.com direkt. Einloggen, Connectors → Matomo klicken, Zugangsdaten einfügen, MCP-API-Key erzeugen — fertig. Kein Docker, kein
git clone, kein lokaler Server.
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.
Voraussetzungen
Die vollständige Setup-Anleitung ist in den Connector eingebaut (im Store sichtbar, wenn du den Connector auswählst). Benötigte Umgebungsvariablen für diesen Connector:
MATOMO_URL, MATOMO_TOKEN
Schritt 1 — Zugangsdaten holen
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)
Schritt 2 — Adapter installieren
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
Schritt 3 — Connector in Gemini hinzufügen
Gemini CLI liest MCP-Server aus ~/.gemini/settings.json (oder %APPDATA%\gemini\settings.json unter Windows). Hinzufügen:
{
"mcpServers": {
"anythingmcp": {
"httpUrl": "https://cloud.anythingmcp.com/mcp",
"headers": { "Authorization": "Bearer YOUR_MCP_API_KEY" }
}
}
}
- Hole deinen MCP API Key aus AnythingMCP → Profil → MCP API Keys → Neuer Key.
- Speichern und
geminineu starten. /mcpin Gemini CLI ausführen —Matomosollte als verfügbar gelistet sein.- Vertex AI Studio:
https://cloud.anythingmcp.com/mcpimtools-Array der Anfrage mit demselben Bearer-Header übergeben.
Verfügbare Tools
| 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
Unterstützen Gemini 1.5 Pro oder 2.x MCP? Ja — Gemini CLI ≥ 0.4 und die Vertex AI Tools API akzeptieren MCP httpUrl-Connectors mit Bearer-Header.
Nächste Schritte
War dieser Guide hilfreich?
