MCP Fathom Analytics
MCP Fathom Analytics
Ein inoffizieller Model Context Protocol ( MCP )-Server für den Zugriff auf Fathom Analytics- Daten über einen KI-Assistenten. Diese Implementierung nutzt das inoffizielle SDK @mackenly/fathom-api zur Interaktion mit der Fathom Analytics API. Es besteht keine Verbindung zu Fathom Analytics und wird von diesem weder empfohlen noch unterstützt. Veröffentlichung auf npm als npx-Skript .
Merkmale
Der MCP-Server bietet die folgenden Fathom Analytics-Tools:
Kontoinformationen
get-account: Rufen Sie Details zu Ihrem Fathom Analytics-Konto ab
Standortverwaltung
list-sites: Listen Sie alle Ihre Fathom Analytics-Sites auf
Veranstaltungen
list-events: Listet Ereignisse für eine bestimmte Site auf
Analyse
get-aggregation: Generieren Sie aggregierte Analyseberichte mit flexiblen Filter- und Gruppierungsoptionen
Besucherverfolgung
get-current-visitors: Erhalten Sie Echtzeitdaten über aktuelle Site-Besucher
Related MCP server: @datafast/mcp-server
Verwendung
Wenn Sie Claude Desktop verwenden, können Sie den MCP-Server mithilfe der JSON-Konfiguration hinzufügen ( weitere Informationen ). Hier ist ein Beispiel:
{
"mcpServers": {
"fathom-analytics": {
"command": "npx",
"args": [
"-y",
"mcp-fathom-analytics"
],
"env": {
"FATHOM_API_KEY": "your_api_key_here"
}
}
}
}Weitere Informationen zu anderen MCP-Clients finden Sie hier: Model Context Protocol Beispiel-Clients
API-Struktur
Der MCP-Server verwendet das SDK @mackenly/fathom-api zur Schnittstelle mit den Fathom Analytics API-Endpunkten:
Konto-API :
https://api.usefathom.com/v1/accountSites-API :
https://api.usefathom.com/v1/sitesEreignis-API :
https://api.usefathom.com/v1/sites/SITE_ID/eventsAggregations-API :
https://api.usefathom.com/v1/aggregationsAktuelle Besucher-API :
https://api.usefathom.com/v1/current_visitors
Aggregationsbeispiele
Das Aggregationstool ist äußerst flexibel. Hier sind einige Anwendungsbeispiele:
Tägliche Seitenaufrufstatistiken der letzten 30 Tage :
{
"entity": "pageview",
"entity_id": "SITE_ID",
"aggregates": "pageviews,uniques,visits",
"date_grouping": "day",
"date_from": "2023-08-01 00:00:00"
}Leistung einzelner Seiten :
{
"entity": "pageview",
"entity_id": "SITE_ID",
"aggregates": "pageviews,uniques,avg_duration",
"field_grouping": "pathname",
"sort_by": "pageviews:desc",
"limit": 10
}Verkehr aus bestimmten Ländern :
{
"entity": "pageview",
"entity_id": "SITE_ID",
"aggregates": "visits",
"field_grouping": "country_code",
"sort_by": "visits:desc"
}Beitragen
Beiträge sind willkommen! Senden Sie gerne einen Pull Request.
Lizenz
Dieses Projekt ist unter der MIT-Lizenz lizenziert – Einzelheiten finden Sie in der Datei LICENSE.
Available Tools
5 toolsget-accountB
Get Fathom Analytics account information
Inputs: no named parameters.
get-aggregationC
Get aggregated analytics data from Fathom
Inputs: entity (required), entity_id (required), aggregates (required), date_from (required), +7 more.
get-current-visitorsC
Get current visitors for a Fathom Analytics site
Inputs: site_id (required), detailed.
list-eventsB
List all events for a Fathom Analytics site (automatically handles pagination)
Inputs: site_id (required), limit.
list-sitesC
List all Fathom Analytics sites on the account
Inputs: limit.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 5 tools
Each tool has a clearly distinct purpose targeting different resources: account info, aggregated data, current visitors, events, and sites. There is no overlap in functionality, making it easy for an agent to select the right tool without confusion.
All tool names follow a consistent verb_noun pattern using hyphen-separated lowercase words (e.g., get-account, list-sites). The naming is predictable and uniform across all tools, enhancing readability and usability.
With 5 tools, the server is well-scoped for analytics purposes, covering key operations like retrieving account details, aggregated data, real-time visitors, events, and sites. Each tool earns its place without being overly sparse or bloated.
The tool set provides comprehensive read-only coverage for analytics data, including account, sites, events, and current visitors. A minor gap exists in write operations (e.g., creating or updating sites/events), but agents can still perform most common analytics tasks effectively.
Maintenance
Related MCP Connectors
Privacy-first, cookie-free web analytics. Read stats and manage sites from your AI.
AI access to Hitsteps analytics, live visitors, uptime, goals, alerts, and chats.
Ask an assistant about your website traffic. Privacy-first web analytics, no cookies. OAuth.
Privacy-first web analytics. Query pageviews, referrers, trends, and AI insights.
Related MCP Servers
- AlicenseAqualityCmaintenanceEnables AI assistants to query privacy-first web analytics from Measure.events, including pageviews, top pages, referrers, and custom event tracking, all via natural language.62MIT
- AlicenseAqualityDmaintenanceExposes DataFast analytics as tools for AI assistants, enabling natural language queries about website metrics such as visitors, referrers, revenue, and real-time data.221MIT
- FlicenseNot gradedqualityDmaintenanceConnects AI assistants to the Fathom meeting recording API to retrieve meeting summaries, transcripts, and action items.-
- AlicenseAqualityFmaintenanceUnofficial MCP server that lets AI agents query Aptabase analytics using cookie-authenticated dashboard endpoints, providing tools for metrics, events, and sessions.171MIT