Skip to main content
Glama
Sign In
Breakage Calendar MCP server

Breakage Calendar MCP server

by CyberNative-AI
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Hybrid

Dated breaks in a local repository

check_repository
Read-onlyIdempotent

Scans a local project folder against Breakage Calendar dates to reveal which upcoming upstream changes will break it, listing affected lines and tested fixes without uploading any data.

Instructions

Reads a local project folder (text files only; skips .git, node_modules, virtual environments and build output) and runs every Breakage Calendar date's published search over it: which dated upstream changes will break this repository, on which line, and the tested fix. Nothing from the folder is sent anywhere. The folder must be inside a folder this server may read: its working folder and BREAKAGE_CALENDAR_ROOTS, or, when the client chose folders, only those.

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": "check_repository"
  }
}

Input Schema

NameRequiredDescriptionDefault
pathNoFolder to read, absolute or relative to the first folder this server may read (default ".")
days_aheadNoReport 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.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4/5.0
Behavior5/5

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

Annotations already declare readOnly/idempotent/non-destructive, and the description still adds real substance: text files only, explicit skip list (.git, node_modules, virtual environments, build output), and a privacy guarantee that nothing from the folder is sent anywhere. It also discloses the permission model — working folder plus BREAKAGE_CALENDAR_ROOTS, or only client-chosen folders when the client picked them — which an agent cannot derive from the annotations.

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

Conciseness5/5

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

Two sentences, both load-bearing: the first carries capability, filtering, and output shape, the second carries privacy and the access precondition. The core action is front-loaded in the opening clause, and there is no boilerplate or restatement of the title.

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 steps in to describe what comes back (breaking change, affected line, tested fix) and covers filtering, privacy, and authorization preconditions. What is missing is any sense of result shape or failure behavior — e.g. what happens when the path falls outside a permitted root, or how a large repository's findings are presented.

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 path and days_ahead are already documented at the structured level, including ranges, defaults, and the always-included recent/late dates. The prose adds no additional syntax, format, or edge-case meaning for either parameter, so the baseline 3 applies.

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?

Names a concrete verb and resource — reads a local project folder and runs every published Breakage Calendar search over it — and states the payoff (which dated upstream changes break the repo, on which line, plus the tested fix). That is far more specific than a generic 'check'. It never names a sibling such as check_dependencies or check_files, so an agent must infer the boundary between them from the phrase 'text files only' rather than from an explicit contrast.

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

Usage Guidelines3/5

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

Usage is only implied: the reader infers you call this to test a repository against the Breakage Calendar. There is no when-to-use versus when-not-to-use guidance, and no hint of how it differs in intent from check_dependencies or check_files, which sound like close substitutes. The access precondition (folder must sit under a readable root) is spelled out, but that is a hard constraint, not routing guidance.

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

Deploy Server

Other Tools