Claude MarketplacesSubmit
weiseer avatar

api-changelog

weiseer/api-changelog-mcp

If your agent needs to know whether upgrading from Anthropic SDK 0.25 to 0.30 will break its code, this saves you from burning tokens on GitHub scraping. It tracks 18 SDKs that AI tooling depends on (Anthropic, OpenAI, LangChain, MCP, Mistral, Vercel AI, and others) and pre-classifies breaking changes so you can call check_version with your current version or pull get_recent_breaking to see what changed across the ecosystem in the last 30 days. The four tools (list_tracked, get_package, get_recent_breaking, check_version) replace what would otherwise be 5 to 15 seconds of release feed parsing with a sub-100ms lookup.

tools
4
transport
STDIO
env vars
2
last updated
May 30, 2026
View on GitHub

Tools

4 tools

Public tool metadata for what this MCP can expose to an agent.

list_trackedPackages we track + latest version + 30d breaking-change count.

Packages we track + latest version + 30d breaking-change count.

No parameter schema in public metadata yet.

get_packageFull record with recent breaking events + GitHub release URL.

Full record with recent breaking events + GitHub release URL.

No parameter schema in public metadata yet.

get_recent_breakingBreaking changes across all packages, filterable.

Breaking changes across all packages, filterable.

No parameter schema in public metadata yet.

check_version"I'm on v X — am I behind, and what breaks if I upgrade?"

"I'm on v X — am I behind, and what breaks if I upgrade?"

No parameter schema in public metadata yet.

Sponsors

Promote your product hereReach 125k+ visitors monthlyPromote your product hereReach 125k+ visitors monthlyAgent CaffeineSponsoredClose your lid, come back to finished workSnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthlyWaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthlyknobsSponsoredSee your site on any phone, any day, in any language

Configuration

API_CHANGELOG_URL

Override remote snapshot URL

API_CHANGELOG_LOCAL_ONLY

Skip remote fetch

Readme

@weiseer/api-changelog-mcp

SDK breaking-change tracker as a stdio MCP server.

Probe P-004 by weiseer.

What it does

Tracks latest version + breaking changes for SDKs AI agents depend on (Anthropic, OpenAI, Google GenAI, MCP SDK, LangChain, LlamaIndex, Mistral, Cohere, Vercel AI, Next.js, React, HuggingFace, Replicate, Ollama).

Your agent can:

  • list_tracked — packages we track + latest version + 30d breaking-change count
  • get_package — full record with recent breaking events + GitHub release URL
  • get_recent_breaking — breaking changes across all packages, filterable
  • check_version — "I'm on v X — am I behind, and what breaks if I upgrade?"

Why use this instead of your agent scraping GitHub releases

Agent DIYapi-changelog
Releases to fetch18 GitHub repo release feeds1 MCP call
Token cost$0.06-0.20$0 free / $0.00005 paid
Latency5-15 seconds<100ms
Breaking-change classificationLLM-classified per callPre-classified once

Install

npm install -g @weiseer/api-changelog-mcp

Use with Claude Desktop / Cursor / Cline / Continue / Windsurf

View the full README on GitHub

Details

Repository
github.com/weiseer/api-changelog-mcp
Category
AI & LLM Tools
Package
@weiseer/api-changelog-mcp
Transport
STDIO
Registry
MCP registry, active

More from weiseer

Related AI & LLM Tools MCP servers

View all
1weiseer avatarstatus-aggregatorweiseer/status-aggregator-mcpCross-vendor SaaS status aggregator for AI agents (Anthropic/OpenAI/AWS/GH/Stripe/CF).0stars
2zentricprotocol avatarZentric Protocol Mcpzentricprotocol/zentricprotocolPrompt injection + PII detection for LLM apps and agent pipelines. Deterministic, sub-25ms.0stars
3maindexapp avatarMaindex Smart Memory Servicemaindexapp/maindexSimple agent memory MCP: keep, recall, update, forget; shared team graph on Maindex.0stars
4megamind-0x avatarSkillAuditmegamind-0x/skillauditSecurity scanner for AI agent skills and MCP servers. Detects credential theft, data exfiltration, prompt injection, obfuscated code, and 80+ threat patterns. F0stars
5securityscan-api avatarSecurityScansecurityscan-api/securityscan-apiScan GitHub-hosted AI skills for vulnerabilities: prompt injection, malware, OWASP LLM Top 10.0stars
6nexus-api-lab avatarNexus Mcpnexus-api-lab/nexus-mcpJapanese LLM security — prompt injection detection (jpi-guard) + PII masking (PII Guard). Free.0stars