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 augmentedstartups · MCP Server · ★ 123
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is VisionCraft-MCP-Server safe to install? View the security audit →
VisionCraft MCP Server 📺 VisionCraft MCP Demo ❌ Without VisionCraft MCP AI assistants struggle with computer vision and Gen-AI knowledge: ❌ Limited understanding of cutting-edge computer vision algorithms ❌ Outdated information on models released after training cutoff ❌ Generic answers that lack depth and technical accuracy ❌ No awareness of latest frameworks and tools ✅ With VisionCraft MCP VisionCraft MCP delivers up-to-date, specialized computer vision and Gen-AI knowledge directly to Claude and other AI assistants. ✅ Specialized knowledge on state-of-the-art computer vision and Gen-AI ✅ Up-to-date information on the newest models and techniques ✅ Detailed, technically accurate responses to complex queries ✅ Full awareness of lat
| Stars | 123 |
| Forks | 7 |
| Language | JavaScript |
| Category | MCP Server |
| License | MIT |
| Quality Score | 65.1003233586005/100 |
| Open Issues | 3 |
| Last Updated | 2025-09-19 |
| Created | 2025-05-06 |
| Platforms | claude-code, mcp, node |
| Est. Tokens | ~1816k |
Explore other popular mcp server tools:
VisionCraft-MCP-Server is VisionCraft MCP delivers up-to-date, specialized computer vision and Gen-AI knowledge directly to Claude and other AI assistants.. It is categorized as a MCP Server with 123 GitHub stars.
VisionCraft-MCP-Server is primarily written in JavaScript.
You can find installation instructions and usage details in the VisionCraft-MCP-Server GitHub repository at github.com/augmentedstartups/VisionCraft-MCP-Server. The project has 123 stars and 7 forks, indicating an active community.
VisionCraft-MCP-Server is released under the MIT license, making it free to use and modify according to the license terms.
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: