by slothflowlabs · MCP Server · ★ 1.6k
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
None of the 44 rules matched — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against 44 published rules built on the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
The quality score combines nine heuristic checks of the repo and its README: completeness, clarity, specificity, examples, structure, agent readiness, step-by-step content, instruction quality and security notes. It rates how well the project explains itself to an agent, not the code.
| Stars | 1,553 |
| Forks | 120 |
| Language | Rust |
| Category | MCP Server |
| License | Apache-2.0 |
| Quality Score | 57/100 |
| Open Issues | 80 |
| Last Updated | 2026-11-06 |
| Created | 2026-05-21 |
| Platforms | mcp, rust |
| Est. Tokens | ~34k |
One pipeline. Write it, wire it, or draw it. Duckle is the open, single-engine ELT stack. One pipeline format, compiled to SQL on DuckDB: write it in Python, wire it from 350+ connectors and components, or draw it on the canvas - or describe it to Duckie, the on-device AI assistant, and verify what it builds. In-pipeline transforms, data quality, and lineage travel with the same artifact.
These tools work well together with duckle for enhanced workflows:
Looking for a duckle alternative? If you're comparing duckle 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.
data load tool (dlt) is an open source Python library that makes data loading easy 🛠️
Agent-ready RPA suite with out-of-the-box automation tools. Built for individuals and enterprises.
Magicrew. The first open-source all-in-one AI productivity platform (Generalist AI Agent + Workflow Engine + I
Where data access meets operational intelligence
Create AI Agents in a No-Code Visual Builder or TypeScript SDK with full 2-way sync. For shipping AI assistant
Low code tool to rapidly build and coordinate multi-agent teams
Explore other popular mcp server tools:
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 44 published rules, covering credential harvesting, data exfiltration, curl | sh installers and more. 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: