crust — security grade SAFE, quality 66/100

Security audit verdict: SAFE · quality 66/100

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 chenxin-yan · MCP Server · ★ 404

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

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

About crust

Crust A TypeScript-first, Bun-native CLI framework with composable modules. Website & Docs   •   Contributing   •   Issues   •   Discord What is Crust? Crust is a modern CLI framework built specifically for TypeScript and Bun. It provides a modular architecture for building command-line tools with features like command routing, argument parsing, interactive prompts, validation, and persistence—all with first-class TypeScript support. Who uses Crust? Nia CLI by Nozomio Labs Getting Started Packages Description

agentagent-toolingcliframeworkjavascripttypescript

Quick Facts

Stars404
Forks10
LanguageTypeScript
CategoryMCP Server
LicenseMIT
Quality Score66.1831381539678/100
Open Issues25
Last Updated2026-09-15
Created2026-02-12
Platformscli, mcp, node
Est. Tokens~15k

Compatible Skills

These tools work well together with crust for enhanced workflows:

  • os-eco — semantic(0.32)+complementary+same_lang+similar_pop+shared_platform (61%)
  • AgenticFORGE — semantic(0.26)+complementary+same_lang+similar_pop+shared_platform (59%)
  • xint — semantic(0.24)+complementary+same_lang+similar_pop+shared_platform (58%)
  • sprout — semantic(0.22)+complementary+same_lang+similar_pop+shared_platform (58%)

crust alternative? Top 6 similar tools

Looking for a crust alternative? If you're comparing crust 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.

  • mcp-agent-langchainjs by Azure-Samples · ⭐ 194

    Serverless AI agent using LangChain.js and Model Context Protocol (MCP) integration to order burgers from a bu

  • frontmcp by agentfront · ⭐ 146

    TypeScript-first framework for the Model Context Protocol (MCP). You write clean, typed code; FrontMCP handles

  • Agently by AgentEra · ⭐ 1.7k

    [GenAI Application Development Framework] 🚀 Build GenAI application quick and easy 💬 Easy to interact with

  • better-agents by langwatch · ⭐ 1.6k

    Standards for building agents, better

  • agents by inkeep · ⭐ 1.4k

    Create AI Agents in a No-Code Visual Builder or TypeScript SDK with full 2-way sync. For shipping AI assistant

  • xmcp by basementstudio · ⭐ 1.3k

    The TypeScript MCP framework

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular TypeScript Agent Tools

Frequently Asked Questions

What is crust?

crust is A TypeScript CLI framework for humans and agents. Every command doubles as an agent skill and MCP tool.. It is categorized as a MCP Server with 404 GitHub stars.

What programming language is crust written in?

crust is primarily written in TypeScript. It covers topics such as agent, agent-tooling, cli.

How do I install or use crust?

You can find installation instructions and usage details in the crust GitHub repository at github.com/chenxin-yan/crust. The project has 404 stars and 10 forks, indicating an active community.

What license does crust use?

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

What are the best alternatives to crust?

The top alternatives to crust on Agent Skills Hub include mcp-agent-langchainjs, frontmcp, Agently. 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