Provides tools for auditing SemVer 2.0 breaking changes, including AST public API surface diffs, parameter reordering, and removed exports.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@genpark-semver-breaking-change-auditor-skill Audit this Python diff for SemVer breaking changes and give a refactoring plan."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
🌐 GenPark MCP Hub Showcase • 📦 Official Website • 📖 Documentation
genpark-semver-breaking-change-auditor-skill is a deterministic, zero-dependency Python skill engineered with 100% production-grade functional parity for autonomous coding agents, Python AST static analysis, codebase refactoring, and architectural dependency auditing.
Executive Capability: Semantic versioning (SemVer 2.0) breaking change auditor inspecting AST public API surface diffs, parameter reordering, and removed exports.
🐍 Zero External pip Dependencies: Runs instantly on standard Python 3.9+ using built-in ast and pure graph algorithms.
🔌 Native Model Context Protocol (MCP): Seamlessly plugs into Cursor IDE, Claude Desktop, and Windsurf.
🎯 100% Deterministic AST Code Parsing: Real syntax-tree traversals, cyclomatic complexity calculations, and dependency graphs without regex guesswork.
🚀 Token Efficiency Optimization: Minimizes LLM context waste by pruning dead code, detecting breaking API surface diffs, and pinpointing refactoring hotspots.
Related MCP server: genpark-monorepo-dependency-cycle-detector-skill
graph LR
User([💻 Developer / Coding Agent]) -->|AST Query & Code Snippet| MCP[⚡ MCP Server / CLI]
MCP --> Client[🛠️ Code Refactoring Client]
Client --> AST[🧠 Python AST & Static Analysis Kernel]
AST --> Output[📊 Refactoring Plan & Graph Metrics]
Output --> Userpython example_usage.pyfrom client import SemverBreakingChangeAuditor
client = SemverBreakingChangeAuditor()
result = client.run_benchmark_semver_audit()
print(result)Connect this skill to Claude Desktop, Cursor, or any MCP-compliant client:
claude_desktop_config.json{
"mcpServers": {
"genpark-semver-breaking-change-auditor-skill": {
"command": "python",
"args": ["/path/to/genpark-semver-breaking-change-auditor-skill/mcp_server.py"]
}
}
}Parameter | Type | Required | Description |
|
| Yes | Source code string, package manifests, or symbol AST tree |
|
| Yes | Standardized response schema containing AST diffs and refactoring telemetry |
GenPark AI Agent Skills are engineered with zero external dependencies using pure Python standard library code. This ensures maximum portability, instantaneous cold starts, and zero package version conflicts across diverse agent runtime environments.
Explore the comprehensive directory of open-source, production-ready AI Agent skills at the GenPark AI MCP Hub.
Run python mcp_server.py --test to verify MCP protocol discovery and tool schema negotiation.
This server cannot be deployed
Check exact npm/PyPI upgrades for evidence-backed breaking changes; query APIs and components.
Monitor third-party API changes in GitHub repos, map breaks to files, open reviewable auto-fix PRs.
Diff two npm/PyPI versions or lockfiles: new install scripts, network/shell/eval calls, new deps.
Code intelligence platform for AI agents. 20 tools for architecture, security & impact analysis.
