No install? Use cloud.anythingmcp.com directly.
Sign in, install the Fathom Analytics in one click, paste the credentials, mint an MCP API key — done. No Docker, no git clone, no local server to run.
TL;DR
Read Fathom Analytics (privacy-friendly web analytics) from any AI agent: aggregations, pageviews, events, sites, custom domains. 6 tools, Bearer auth.
💡 ¿Sin instalación? Usa cloud.anythingmcp.com directamente. Inicia sesión, pulsa Connectors → Fathom Analytics, pega tus credenciales, genera una MCP API key — listo. Sin Docker, sin
git clone, sin servidor local.
Fathom Analytics + Gemini
Read Fathom Analytics (privacy-friendly web analytics) from any AI agent: aggregations, pageviews, events, sites, custom domains. 6 tools, Bearer auth.
Requisitos previos
Las instrucciones de configuración completas están incluidas en el conector (visibles en el store al seleccionarlo). Las variables de entorno requeridas:
FATHOM_API_TOKEN
Paso 1 — Obtener credenciales
com/api).
Setup:
- Sign in to https://app.usefathom.com → top-right avatar → Account → API Keys → Generate a new API key.
- Pick scopes: at minimum 'sites:read' + 'aggregations:read'.
- Set
FATHOM_API_TOKEN.
Authentication: Authorization: Bearer ${FATHOM_API_TOKEN}.
Aggregations API: the most useful — flexible querying like Stripe Sigma. Pass entity, entity_id, aggregates, date_grouping, filters, etc. Returns rows of data.
…(continued in the in-app connector instructions)
Paso 2 — Instalar el adapter
git clone https://github.com/HelpCode-ai/anythingmcp.git
cd anythingmcp && docker compose up -d
Paso 3 — Añadir el conector en Gemini
Gemini CLI lee servidores MCP desde ~/.gemini/settings.json (o %APPDATA%\gemini\settings.json en Windows). Añade:
{
"mcpServers": {
"anythingmcp": {
"httpUrl": "https://cloud.anythingmcp.com/mcp",
"headers": { "Authorization": "Bearer YOUR_MCP_API_KEY" }
}
}
}
- Obtén tu MCP API key desde AnythingMCP → Perfil → MCP API Keys → Nueva Key.
- Guarda el archivo y reinicia
gemini. - Ejecuta
/mcpen la Gemini CLI —Fathom Analyticsdebería aparecer como disponible. - Vertex AI Studio: pasa
https://cloud.anythingmcp.com/mcpal arraytoolsde tu petición con el mismo header Bearer.
Herramientas disponibles
| Tool | What it does |
|---|---|
fathom_current_user | Return account info: id, name, email |
fathom_list_sites | List Fathom sites tracked |
fathom_list_events | List events (conversion goals) for a site |
fathom_aggregations | Run an aggregation query — Fathom's main analytics endpoint |
fathom_current_visitors | Get the current number of visitors on a site (real-time) |
fathom_create_event | Create a new event (conversion goal) for a site |
FAQ
¿Gemini 1.5 Pro o 2.x soportan MCP? Sí — Gemini CLI ≥ 0.4 y la API de tools de Vertex AI aceptan conectores MCP httpUrl con header Bearer.
Siguientes pasos
¿Te ha sido útil esta guía?