by matthew-kissinger · MCP Server · ★ 98
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
Text-to-3D as code: language models write JavaScript programs that build game-ready GLBs, look at their own renders, and revise. Ships as an MCP server plus skills for any harness.
| Stars | 98 |
| Forks | 8 |
| Language | TypeScript |
| Category | MCP Server |
| License | MIT |
| Quality Score | 53.4984483268/100 |
| Last Updated | 2026-09-17 |
| Created | 2026-06-23 |
| Platforms | claude-code, mcp, node |
| Est. Tokens | ~13k |
Looking for a kiln alternative? If you're comparing kiln 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.
🏛 [UNDER CONSTRUCTION] A (roman) claude plugin marketplace
📜 An MCP server for conversation history search and retrieval in Claude Code
Governance gateway for AI agents — bounded, auditable, session-aware control with MCP proxy, shell proxy & HTT
Build interactive 3D worlds with high-quality assets from Thrixel and your AI agent of choice.
Cheapest Money-Saving Self-hosted AI agent workspace with tool calling, MCP, multi-model routing, sandboxed ex
3D AI agent platform for the browser. Load any GLB/glTF avatar, give it an LLM brain with memory, emotions, an
Explore other popular mcp server tools:
kiln is Text-to-3D as code: language models write JavaScript programs that build game-ready GLBs, look at their own renders, and revise. Ships as an MCP server plus skills for any harness.. It is categorized as a MCP Server with 98 GitHub stars.
kiln is primarily written in TypeScript. It covers topics such as 3d, agent-tools, ai-agents.
You can find installation instructions and usage details in the kiln GitHub repository at github.com/matthew-kissinger/kiln. The project has 98 stars and 8 forks, indicating an active community.
kiln is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to kiln on Agent Skills Hub include claude-emporium, claude-historian-mcp, deterministic-agent-control-protocol. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
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: