Skip to main content
Glama
nixkeeper-mcp
by nixkeeper

Packages needing attention

needs_attention
Read-only

Identify crucial package maintenance items in nixpkgs. Track build failures, outdated dependencies, and security vulnerabilities needing immediate fixes for specific teams or maintainers.

Instructions

Packages that need attention, as nixkeeper's dashboard counts them: a build failing on Hydra, outdated, vulnerable, or a CVE fix to backport; optionally only one maintainer's (GitHub handle), one team's or one list's, one kind, one platform. Without maintainer, team or list: all of nixpkgs (thousands: narrow with kind). With a maintainer or team, also the open PRs they can merge now with the merge bot (canMerge).

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": "needs_attention"
  }
}

Input Schema

NameRequiredDescriptionDefault
kindNoany (default): what the dashboard says needs attention; failing (a build of its own fails), updateFailing (the update bot fails), outdated, waiting (updated on master, waiting for the channel), vulnerable, backport, broken; stagingNext: builds on master but fails its own build on staging-next (a forecast: it fails on master when staging-next is merged, unless fixed; not in any); all: every package of the maintainer/team/list.
listNoOne of the dashboard's lists.
teamNoA nixpkgs team (Gaming, Qt-KDE, ...).
limitNoAt most this many results (default 50).
queryNoInstead of the others: the dashboard page's search, as its box takes it (is:builds on:darwin team:Gaming wine). is: one card (outdated, failed, builds, updates, vulnerable, backport, broken, staging-next-breaks), is:unbuilt, -is:broken, has:pr, -has:pr, -has:maintainer, on:linux or on:darwin, in: a package set (python313Packages, top-level), team:, by: or @handle, and words of a name. Without is:, every package of the maintainer's or team's, as the page lists them. Other words (age:, sort:...) are refused; the answer's query.page links the page with the query.
platformNolinux or darwin: available there (for failing: failing there).
maintainerNoA maintainer's GitHub handle.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.5.1
    • addedInput schema / properties / query
      Added value: +{
      +  "description": "Instead of the others: the dashboard page's search, as its box takes it (is:builds on:darwin team:Gaming wine). is: one card (outdated, failed, builds, updates, vulnerable, backport, broken, staging-next-breaks), is:unbuilt, -is:broken, has:pr, -has:pr, -has:maintainer, on:linux or on:darwin, in: a package set (python313Packages, top-level), team:, by: or @handle, and words of a name. Without is:, every package of the maintainer's or team's, as the page lists them. Other words (age:, sort:...) are refused; the answer's query.page links the page with the query.",
      +  "type": "string"
      +}
  2. First observedv0.3.0

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already declare readOnlyHint and openWorldHint, and the description adds real context beyond them: cross-parameter behavior (maintainer/team silently widen results to include canMerge PRs), the stagingNext forecast semantics, and that unsupported query words are refused with a query.page link returned. No auth or rate-limit notes, but the behavioral picture is substantially richer than the annotations alone.

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

Conciseness3/5

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

Purpose and the all-of-nixpkgs caveat are front-loaded, which is good, but the three sentences are long and clause-heavy, and much of the query grammar (is:, on:, team:, by:, refused sort:/age:) duplicates what the schema already says. Trimming the restated query syntax would make it tighter without losing information.

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 7-parameter, all-optional, no-output-schema tool, the description covers defaults (limit 50, kind any), the narrowing strategy, and cross-parameter side effects, and hints at the response shape via 'the answer's query.page'. What is missing is any statement of what a single package entry contains, which matters since no output schema exists.

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 semantics the schema does not encode: the interaction where maintainer/team also surface open mergeable PRs, and the 'instead of the others' relationship of query to the filter parameters. That justifies going above baseline, though most per-parameter detail is a restatement of the schema.

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?

Names a specific resource and scope: 'packages that need attention, as nixkeeper's dashboard counts them', and enumerates the concrete categories (failing, outdated, vulnerable, backport) that define the set. That framing separates it cleanly from siblings like build_failures, vulnerabilities, or find_packages, which each cover only one slice.

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?

Gives explicit operational conditions: without maintainer/team/list you get all of nixpkgs (thousands), so narrow with kind; with a maintainer or team you additionally get mergeable PRs. It also states the query parameter is an alternative to the filters. It stops short of naming sibling tools to use instead, so not a 5.

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