Skip to main content
Glama

Read a site's real visitors

get_site_visitors
Read-only

Retrieve daily real-visitor counts for one or all hosted sites, excluding crawlers and bots, with traffic sources, returning visitors, and period totals for reporting.

Instructions

Real people on the caller's own hosted sites, per day — the platform's visitor count, with crawlers, cloud servers and the operator left out (a visitor is a browser that ran one of the site's scripts). For each day: visitors, returning visitors (seen in the 30 days before), where they came from (google, search, social, ai assistants, qu4zr sites, other links, direct), and every request vs. bot requests. Also the totals for the window and for the same-length window just before it. Without domainId: every site of the caller, busiest first, totals and a per-day trend — the place to start a traffic report. With domainId: that site day by day. Works whether or not the app records analytics.track events. Counted per site and per day (one person on three days = three); refreshed every few hours, so today is marked partial. Days default 30, up to 400.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "get_site_visitors"
  }
}

Input Schema

NameRequiredDescriptionDefault
daysNoWindow in days, ending today (default 30).
domainIdNoOne site (from list_domains). Omit for all of the caller's sites.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.53.0

TDQS

A4.3/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations only say readOnlyHint=true; the description adds substantial behavior: bot/crawler exclusion, the counting rule (one person on three days = three), a refresh cadence of a few hours with today flagged partial, and inclusion of a prior-period comparison window. These are exactly the traits an agent cannot infer from annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Long but dense — the definition of visitor, the no-domainId behavior, and the partial-today caveat are all front-loaded before edge details. A few clauses (the 30-day returning-visitor rule, the traffic-source taxonomy) are verbose but genuinely informative rather than filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

There is no output schema, and the description compensates by enumerating the returned fields — visitors, returning visitors, traffic sources, requests vs. bot requests, totals and prior-period totals. For a two-parameter read tool, an agent has everything needed to call it and interpret the result.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, but the description adds meaning: without domainId results are ordered busiest first with totals and a per-day trend, and with it the site is returned day by day. It also restates the days default and 400 cap, which the schema already carries.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource plus scope: real human visitors per day on the caller's own hosted sites, with crawlers and cloud servers excluded, and a precise definition of 'visitor'. The dual behavior (all sites vs. one domainId) is spelled out. It does not explicitly differentiate from the near sibling get_site_traffic, so it stops short of a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

"the place to start a traffic report" gives clear default-usage guidance, and "Works whether or not the app records analytics.track events" implicitly positions it against event-based analytics tools. It never names an alternative tool or states when NOT to use it, so explicit exclusion guidance is missing.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.