Breakage Calendar MCP server

Dated breaks for a dependency list

check_dependencies

Read-onlyIdempotent

Compare a dependency list against dated upstream changes to identify upcoming breakages and retrieve each tested fix before upgrading, pinning, or deploying.

Instructions

Which dated upstream changes (image tags that move, AI models and APIs that shut down, CI runners that are retired, packages that stop installing) will break these dependencies, and the fix for each, with the day it was tested. Runs each Breakage Calendar date's own published search. Use before upgrading, pinning or deploying. Write each dependency as ecosystem:name[@version]: npm package: npm:express@4.21.0, npm:@scope/name; Python package: pypi:celery==5.4.0, pypi:paramiko; Ruby gem: gem:rails@8.0.2, gem:sidekiq-cron; Go module: go:golang.org/x/crypto@v0.31.0; Maven artifact: maven:com.jcraft:jsch@0.1.55; container image: docker:postgres:latest, docker:node:lts, docker:php:8-apache; GitHub Action: action:actions/setup-python@v5; CI runner label: runner:ubuntu-latest, runner:macos-14; Homebrew formula: brew:node@18; AI model id your code sends: model:gpt-4o, model:claude-sonnet-4-5; R package: cran:decoupleR.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "dependencies": "<dependencies>"
    },
    "name": "check_dependencies"
  }
}

Input Schema

Name	Required	Description	Default
`days_ahead`	No	Report dates up to this many days ahead (default 365). Dates that took effect in the last 30 days, and announced dates that are late, are always included.
`dependencies`	Yes	For example ["docker:postgres:latest", "pypi:celery==5.4.0", "npm:cron@3.1.7", "runner:macos-14", "model:gpt-4o"]

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Nov 14, 2026

TDQS

A4/5.0

Behavior4/5

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

Annotations already declare read-only, idempotent, open-world, non-destructive behavior, so the bar is lower. The description still adds real context: it runs each Breakage Calendar date's own published search (rather than a single global query), reports the fix per break, and includes the day each finding was tested.

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?

The purpose, behavior and timing are front-loaded into two tight sentences, but roughly two-thirds of the text is a long enumeration of dependency formats that would be better placed in the schema's item description or a pattern. Information-dense, yet the sizing is disproportionate to the two-parameter surface.

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?

With no output schema, the description carries the burden of describing returns and does so conceptually (breaks, fixes, tested date). Remaining gaps are minor: no stated response shape, result caps, or pagination/truncation behavior for large dependency lists (up to 1000 items).

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

Parameters3/5

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

Schema coverage is 100%, so both parameters are already self-documenting, which sets the baseline at 3. The description's ecosystem:name[@version] catalog adds genuine grammar detail beyond the schema's five bare examples (scoped npm, Maven group:artifact, action:, brew:, cran:, model:), but it overlaps substantially with the schema's example list rather than adding new semantics.

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 resource and scope: dated upstream changes (moving image tags, shutdown models/APIs, retired runners, broken packages) that will break the supplied dependencies, plus the fix and tested date for each. This is clearly a per-dependency breakage check, distinct from siblings like list_upcoming_breaks (calendar listing) or check_repository (repo-level scan).

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 an explicit timing trigger: 'Use before upgrading, pinning or deploying.' It does not, however, route the agent between this tool and check_repository / check_files / get_break, so the selection guidance stops short of full alternative differentiation.

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

Deploy Server