sloppy MCP Server
Heyosseus/sloppy
[](https://agentrank-ai.com/tool/Heyosseus--sloppy/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge) Static analysis for the debt AI agents leave in PHP: 26 rules, Claude Code hooks, git-diff review, a Rector and Pint fix pass, Pest expectations, CI annotations and an MCP server. Deterministic, local, no LLM.
claude mcp add agentrank -- npx -y agentrank-mcp-server Overview
Heyosseus/sloppy is a PHP MCP server licensed under MIT. Static analysis for the debt AI agents leave in PHP: 26 rules, Claude Code hooks, git-diff review, a Rector and Pint fix pass, Pest expectations, CI annotations and an MCP server. Deterministic, local, no LLM. Topics: ai, code-quality, laravel, linter, php, static-analysis, technical-debt, filament, mcp, pest, pint, rectorphp.
Ranked #371 out of 24846 indexed tools.
In the top 2% of all indexed tools.
Ecosystem
Score Breakdown
157 stars → growing community
Last commit 1mo ago → moderate activity
3/3 issues closed → responsive maintainer
4 contributors → small team
No dependents → no downstream usage
Weights: Freshness 20% · Issue Health 20% · Dependents 22% · Stars 10% · Contributors 8% · How we score →
Matched Queries
From the README
<p align="center">
<picture>
<source media="(prefers-color-scheme: dark)" srcset=".github/assets/logo-dark.svg">
</picture>
</p>
<p align="center">
<b>Your AI agent writes the PHP. Sloppy makes it clean up after itself.</b><br>
It catches the code people regret — god methods, swallowed exceptions, N+1 queries —
inside Claude Code, your CI and your Pest suite.<br>
Deterministic and local: no model, no API key, no network.
</p>
<p align="center">
<a href="https://github.com/heyosseus/sloppy/actions/workflows/tests.yml"></a>
<a href="https://packagist.org/packages/heyosseus/sloppy"></a>
<a href="https://packagist.org/packages/heyosseus/sloppy"></a>
<a href="LICENSE.md"></a>
<a href="https://ko-fi.com/ratirukhadze"></a>
<a href="https://m8ven.ai/mcp/heyosseus/sloppy?s=readme"></a>
</p>
<p align="center">
</p>
<p align="center"><sub>Real output. Claude Code runs this after every edit and hands it to the model, which fixes the catch block before you Read full README on GitHub → Get the weekly AgentRank digest
Top movers, new tools, ecosystem insights — straight to your inbox.