Skip to main content
Glama

packagecloud MCP by usefulapi

Get repository install stats

packagecloud_get_repository_installs
Read-only

How often a repository was installed (set up on a machine): a count, a time series, or (owners only) the detail of each install, optionally for one distro or distro+version. Default range is the last 7 days; pass start_date=19700101Z for all time. GET /repos/{user}/{repo}/stats/installs[/{distro}[/{version}]]/{count|detail|series/}.json.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
kindNocount = total, series = per interval, detail = one record per install (owners only; includes host names and IP addresses).count
pageNoPage number, from 1 (default 1). Pass the previous reply's next_page.
distroNoOnly installs on this distribution, for example ubuntu.
versionNoOnly installs on this distribution version, for example jammy (needs distro).
end_dateNoAn ISO 8601 date, for example 20260101Z or 2026-01-01.
intervalNoSeries interval, "daily" (default) or "weekly".daily
per_pageNoResults per page (default 30; the server caps it at its own Max-Per-Page).
repositoryYesThe repository as "user/repo" (the fqname returned by packagecloud_list_repositories).
start_dateNoAn ISO 8601 date, for example 20260101Z or 2026-01-01.
user_agentNoOnly downloads whose user agent equals this.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so safety is covered. The description adds genuinely non-obvious behavior: detail is owners-only and exposes host names and IP addresses, the default window is 7 days, and start_date=19700101Z unlocks all time — none of which the annotations convey.

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?

Front-loaded with the purpose and the mode enumeration, then defaults and scoping. The trailing raw URL template is dense but does encode the kind/distro/version/interval combinations compactly; nothing is wasted, though it reads as documentation-heavy.

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

Completeness4/5

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

For a 10-parameter, read-only stats tool with no output schema, the definition covers modes, scoping, defaults, and the owners-only privacy caveat. Pagination behavior and the shape of the series output are left to the schema/agent inference, which is a minor gap.

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 the schema lacks: how 'kind' maps onto the URL suffix, that version requires distro, and the trick for querying all time. These cross-parameter relationships raise it above baseline.

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

Purpose5/5

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

States a specific verb+resource ('how often a repository was installed') and enumerates the three output modes (count, series, detail), immediately distinguishing it from the sibling download-statistics tool. An agent can tell what it gets without opening the schema.

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?

Explains when each mode applies ('count/series/detail', detail owners only) and the scoping conditions for distro/version plus the default and all-time date ranges. It does not name a competing sibling tool explicitly, but the selection guidance among modes is clear.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.