ultracite — security grade SAFE, quality 63/100

Security audit verdict: SAFE · quality 63/100

No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by haydenbleasel · MCP Server · ★ 3.3k

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is ultracite safe to install? View the security audit →

About ultracite

Ultracite A production-grade, zero-configuration preset for ESLint, Biome, and Oxlint. Ultracite is designed to help you and your AI models write consistent and type-safe code without the hassle of configuration. Choose your preferred toolchain and get started in seconds. Quick Start The interactive setup will guide you through selecting your formatter/linter, framework, editor, and AI agents. It can also offer to install the reusable Ultracite skill, or you can pass in non-interactive flows. Supported Tools Biome — All-in-one formatting and linting ESLint + Prettier + Stylelint — Most mature ecosystem with the largest plugin support Oxlint + Oxfmt — 50-100x faster than ESLint, part of the Oxc ecosystem Key Features ⚡ Subsecond Performance Built on Rust-based tools for instant code analysis. On-save checks feel seamless without interrupting your workflow. 🎯 Zero-Config by Design Hundreds of preconfigured rules optimized for JavaScript and TypeScript projects. Customize when needed, but it works perfectly out of the box. 🤖 AI-Ready Generate rules for 40+ AI agents including Claude Code, GitHub Copilot, Cursor, Gemini, and more. Ensures consistent code

biomecursorformatterlintermcpvscodewindsurfzed

Quick Facts

Stars3,290
Forks126
LanguageTypeScript
CategoryMCP Server
LicenseMIT
Quality Score62.7079268501991/100
Open Issues3
Last Updated2026-09-19
Created2022-03-18
Platformsmcp, node, vscode
Est. Tokens~14k

ultracite alternative? Top 6 similar tools

Looking for a ultracite alternative? If you're comparing ultracite with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • docs-mcp-server by arabold · ⭐ 1.8k

    Grounded Docs MCP Server: Open-Source Alternative to Context7, Nia, and Ref.Tools

  • fastapi_mcp by tadata-org · ⭐ 12.0k

    Expose your FastAPI endpoints as Model Context Protocol (MCP) tools, with Auth!

  • Unity-MCP by IvanMurzak · ⭐ 4.3k

    AI Skills, MCP Tools, and CLI for Unity Engine. Full AI develop and test loop. Use cli for quick setup. Effici

  • mcp-server-qdrant by qdrant · ⭐ 1.5k

    An official Qdrant Model Context Protocol (MCP) server implementation

  • antigravity-workspace-template by study8677 · ⭐ 1.3k

    Give Claude Code, Cursor, Codex CLI a ChatGPT for your codebase. Multi-agent knowledge engine, grounded Q&A wi

  • atlassian-mcp-server by atlassian · ⭐ 1.1k

    Official remote MCP server for Atlassian. Securely connect Jira, Confluence, Jira Service Management, Bitbucke

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular TypeScript Agent Tools

Frequently Asked Questions

What is ultracite?

ultracite is A highly opinionated, zero-configuration linter and formatter.. It is categorized as a MCP Server with 3.3k GitHub stars.

What programming language is ultracite written in?

ultracite is primarily written in TypeScript. It covers topics such as biome, cursor, formatter.

How do I install or use ultracite?

You can find installation instructions and usage details in the ultracite GitHub repository at github.com/haydenbleasel/ultracite. The project has 3.3k stars and 126 forks, indicating an active community.

What license does ultracite use?

ultracite is released under the MIT license, making it free to use and modify according to the license terms.

What are the best alternatives to ultracite?

The top alternatives to ultracite on Agent Skills Hub include docs-mcp-server, fastapi_mcp, Unity-MCP. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.

The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.

Sources & who's responsible:

View on GitHub → Browse MCP Server tools