cogny clianalyticsfirst 15 calls free

fathom analytics from your shell.

List sites and conversion events, pull aggregate stats with time grouping and filters, and read current visitor counts — all from Bash over the Fathom Analytics MCP. Privacy-friendly analytics, scriptable without the dashboard.

1. sign up, free for the first calls (uses your git email)npx @cogny/cli init --agent claude-code
2. see every Fathom Analytics toolcogny tools list
3. call any tool from bash, no MCP wiringcogny tools call mcp__Fathom_Analytics__aggregate --input '{…}'

Start free @cogny/cli on npm

01two paths

you're a person

Fathom’s single-page dashboard is great for a quick look, but pulling a specific date-grouped breakdown or an event’s conversions means re-filtering and exporting by hand. The CLI returns those aggregates as JSON you can schedule or feed to an agent. Connect Fathom Analytics once in Cogny Solo and let your coding agent, or a scheduled loop, do the querying for you.

Start Solo

you're an agent

Sign yourself up with one command. The CLI issues a key, wires nothing, and exposes every Fathom Analytics tool over JSON-RPC. The first 15 calls are free.

npx @cogny/cli init --agent claude-code

02tools call

real Fathom Analytics tools.

Tool names as the Fathom Analytics MCP serves them. Send --input JSON, get JSON back. The payloads are illustrative.

mcp__Fathom_Analytics__aggregate
Aggregate pageviews, visits, uniques, and bounce rate by day.
- cogny tools call mcp__Fathom_Analytics__aggregate \ --input '{"entity":"pageview","entity_id":"CDBUGS","aggregates":"pageviews,visits,uniques,bounce_rate","date_from":"2026-06-01 00:00:00","date_to":"2026-06-14 23:59:59","date_grouping":"day"}'
example response
```
[
  {
    "date": "2026-06-01",
    "pageviews": 1840,
    "visits": 1212,
    "uniques": 1104,
    "bounce_rate": 0.46
  },
  {
    "date": "2026-06-02",
    "pageviews": 2010,
    "visits": 1388,
    "uniques": 1251,
    "bounce_rate": 0.43
  }
]
```
mcp__Fathom_Analytics__current_visitors
Live visitor count, optionally broken down by page.
- cogny tools call mcp__Fathom_Analytics__current_visitors \ --input '{"site_id":"CDBUGS","detailed":true}'
example response
```
{
  "total": 18,
  "content": [
    {
      "pathname": "/pricing",
      "total": 7
    },
    {
      "pathname": "/",
      "total": 5
    }
  ]
}
```
mcp__Fathom_Analytics__list_events
List configured conversion events for a site.
- cogny tools call mcp__Fathom_Analytics__list_events \ --input '{"site_id":"CDBUGS"}'
example response
```
{
  "object": "list",
  "data": [
    {
      "id": "signup-completed",
      "name": "Signup completed"
    },
    {
      "id": "demo-booked",
      "name": "Demo booked"
    }
  ]
}
```

03tools list

the rest of the surface.

A sample of the other Fathom Analytics tools. Run cogny tools list --json for every tool and its input schema.

mcp__Fathom_Analytics__list_sites
mcp__Fathom_Analytics__list_email_reports

04then a verdict

calls from a script. verdicts from cogny.

Every write is logged with who authorised it. Launches your agent makes (a new campaign, a new ad) become measured tickets automatically; for other changes, your agent offers to register them. Cogny measures each in your own data, three days later for ads and seven for content and SEO, and closes it as worked, partial, didn't work or inconclusive.

worked
Moved the number. Every measured win has a share card.
partial
Some of it did.
didn't work
On the record anyway, so it isn't proposed again.
inconclusive
Not enough data to call.

How the loop works

05questions

questions.

Is this an official Fathom CLI?: No — it is the Cogny CLI calling the Fathom Analytics MCP over the cogny-mcp-proxy. You connect your Fathom API token once in Cogny and then call every tool from Bash with no API plumbing of your own.
Can I get event conversions, not just pageviews?: Yes. Set entity to "event" and entity_id to the event ID in aggregate to pull that conversion’s stats; use list_events first to discover the IDs configured on the site.
What date format do the stats tools expect?: date_from / date_to use "YYYY-MM-DD HH:MM:SS" in UTC, and field_grouping can be hour, day, month, or year. The data is privacy-first — no per-visitor PII, just aggregates.

06related

Building an agent? The full tool map for every server is one fetch: /cli/llms.txt

fathom analytics, then a verdict.

Start free All CLIs