by oxygenframe · MCP Server · ★ 5
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
None of the 42 rules matched — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against 42 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 | 5 |
| Forks | 0 |
| Language | Rust |
| Category | MCP Server |
| License | Apache-2.0 |
| Quality Score | 65/100 |
| Last Updated | 2026-10-27 |
| Created | 2026-10-19 |
| Platforms | browser, claude-code, mcp, rust |
| Est. Tokens | ~23k |
Motion graphics as Rust code, made for AI agents. A scene is an async fn; oxframe check returns a storyboard and a report that points to the line to fix. Native, deterministic rendering to MP4, WebM, ProRes or PNG — no browser, no Node. Text, code, charts, matrices, formulas, 3D, sound.
Looking for a oxframe-sdk alternative? If you're comparing oxframe-sdk 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.
Autodesk Maya MCP adapter for AI agents to inspect scenes, model geometry, edit materials, rig and animate ass
Blender MCP addon for AI agents to model, edit meshes and UVs, rig, build materials and render scenes through
565 AI-callable tools across 16 MCP servers. Full-pipeline AAA game asset production. Controls Blender, Substa
Universal academic document & thesis engine for AI agents and engineers.
Claude Code plugin: describe an object or show a photo, and Claude builds a clean 3D model in Blender, for gam
Skill for shipping a 20-45s SaaS product demo video in Remotion. Built and used in production with Claude Code
Explore other popular mcp server tools:
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 42 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: