Back to MCP directory
publicPublicdnsLocal runtime

mcp-fathom-analytics

一个非官方服务器,允许AI助手访问Fathom Analytics数据,使用户能够获取账户信息、网站统计数据、事件、聚合报告和实时访客跟踪。

article

README

MCP Fathom Analytics

An unofficial Model Context Protocol (MCP) server for accessing Fathom Analytics data through an AI assistant. This implementation uses the @mackenly/fathom-api unofficial SDK to interact with the Fathom Analytics API. Not affiliated, endorsed, or supported by Fathom Analytics. Published to npm as an npx script.

smithery badge

Fathom Analytics MCP server MseeP.ai Security Assessment Badge

Features

The MCP server provides the following Fathom Analytics tools:

Account Information

  • get-account: Retrieve details about your Fathom Analytics account

Sites Management

  • list-sites: List all your Fathom Analytics sites

Events

  • list-events: List events for a specific site

Analytics

  • get-aggregation: Generate aggregated analytics reports with flexible filtering and grouping options

Visitor Tracking

  • get-current-visitors: Get real-time data about current site visitors

Usage

If you're using Claude Desktop, you can add the MCP server using the json config (more info). Here's an example:

{
    "mcpServers": {
        "fathom-analytics": {
            "command": "npx",
            "args": [
                "-y",
                "mcp-fathom-analytics"
            ],
            "env": {
                "FATHOM_API_KEY": "your_api_key_here"
            }
        }
    }
}

You can find more information about other MCP Clients here: Model Context Protocol Example Clients

API Structure

The MCP server uses the @mackenly/fathom-api SDK to interface with the Fathom Analytics API endpoints:

  1. Account API: https://api.usefathom.com/v1/account
  2. Sites API: https://api.usefathom.com/v1/sites
  3. Events API: https://api.usefathom.com/v1/sites/SITE_ID/events
  4. Aggregation API: https://api.usefathom.com/v1/aggregations
  5. Current Visitors API: https://api.usefathom.com/v1/current_visitors

Aggregation Examples

The aggregation tool is highly flexible. Here are some example use cases:

  1. Daily pageview statistics for the last 30 days:
{
  "entity": "pageview",
  "entity_id": "SITE_ID",
  "aggregates": "pageviews,uniques,visits",
  "date_grouping": "day",
  "date_from": "2023-08-01 00:00:00"
}
  1. Performance of individual pages:
{
  "entity": "pageview",
  "entity_id": "SITE_ID",
  "aggregates": "pageviews,uniques,avg_duration",
  "field_grouping": "pathname",
  "sort_by": "pageviews:desc",
  "limit": 10
}
  1. Traffic from specific countries:
{
  "entity": "pageview",
  "entity_id": "SITE_ID",
  "aggregates": "visits",
  "field_grouping": "country_code",
  "sort_by": "visits:desc"
}

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

License

This project is licensed under the MIT License - see the LICENSE file for details.

help

Runtime guide

cloud

Hosted runtime

Hosted servers run from a provider-managed environment. You usually connect the MCP client to the hosted endpoint or follow the provider's authorization flow, without keeping a local process alive

  1. Open provider connection page
  2. Authorize or copy endpoint
  3. Connect from your MCP client
terminal

Local runtime / other methods

Local servers run on your own machine or infrastructure. You normally copy the server_config into your MCP client, install the required package, and provide env variables from env_schema when needed

  1. Copy server_config
  2. Install required package
  3. Fill env variables and restart client