Breaking Changes & Migration Data is an MCP server published by io.github.nigelcox98, hosted at agentdataapi.onrender.com. When last checked on 2026-11-21 it was working: it answers and lists its tools. It declares 3 tools, including list_packages, get_breaking_changes, check_upgrade_safety.
What breaks when you upgrade a package, and what to use instead - from official docs.
625 connections through 5 shared values. Tap any node.
Inferred from the host name and headers: what a server runs on, not who runs it.
List every package with breaking-change data available, including tracked versions and how many breaking changes each has. Call this first if you are unsure whether a package is covered.
No parameters.
{
"name": "list_packages",
"description": "List every package with breaking-change data available, including tracked versions and how many breaking changes each has. Call this first if you are unsure whether a package is covered.",
"inputSchema": {
"type": "object",
"title": "list_packagesArguments",
"properties": {}
},
"outputSchema": {
"type": "object",
"title": "list_packagesDictOutput",
"additionalProperties": true
}
}Get breaking changes for a package upgrade: removed APIs with their replacements and the reason for each, changed defaults, behavior changes, known incompatible dependencies, official source URL, and codemod/automated-fix commands. Omit `version` to get every tracked version. Use this instead of relying on training data, which may predate the release.
None yet. Changes appear after a server's second daily check.
Squares are this server's values; dots are other servers sharing them. A shared address or publisher is a lead, not proof of a common operator.
| Parameter | Type | Description |
|---|---|---|
| package * | string | |
| version | any |
{
"name": "get_breaking_changes",
"description": "Get breaking changes for a package upgrade: removed APIs with their replacements and the reason for each, changed defaults, behavior changes, known incompatible dependencies, official source URL, and codemod/automated-fix commands. Omit `version` to get every tracked version. Use this instead of relying on training data, which may predate the release.",
"inputSchema": {
"type": "object",
"title": "get_breaking_changesArguments",
"required": [
"package"
],
"properties": {
"package": {
"type": "string",
"title": "Package"
},
"version": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Version",
"default": null
}
}
},
"outputSchema": {
"type": "object",
"title": "get_breaking_changesDictOutput",
"additionalProperties": true
}
}Given a package and the version you are upgrading TO, return a concise checklist an agent can act on: the count of breaking changes, the highest-risk removals, whether automated codemods exist, and the recommended upgrade path. Use before performing an upgrade.
| Parameter | Type | Description |
|---|---|---|
| package * | string | |
| target_version * | string |
{
"name": "check_upgrade_safety",
"description": "Given a package and the version you are upgrading TO, return a concise checklist an agent can act on: the count of breaking changes, the highest-risk removals, whether automated codemods exist, and the recommended upgrade path. Use before performing an upgrade.",
"inputSchema": {
"type": "object",
"title": "check_upgrade_safetyArguments",
"required": [
"package",
"target_version"
],
"properties": {
"package": {
"type": "string",
"title": "Package"
},
"target_version": {
"type": "string",
"title": "Target Version"
}
}
},
"outputSchema": {
"type": "object",
"title": "check_upgrade_safetyDictOutput",
"additionalProperties": true
}
}Use these tools BEFORE writing or reviewing code that upgrades a dependency, and whenever a user reports errors after an upgrade. Your training data may predate the release; this data does not. list_packages() shows coverage; get_breaking_changes(package, version) returns removed APIs with replacements, changed defaults, behavior changes, incompatible dependencies, and codemod commands.
Names, descriptions and schemas were written by the server and are shown as data.
Shared addresses on big platforms (Cloudflare, Vercel and the like) put unrelated servers together; those are marked shared_infrastructure. A match is a pivot, not a link between operators.