three.ws — security grade SAFE, quality 56/100

Security audit verdict: SAFE · quality 56/100

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 nirholas · MCP Server · ★ 98

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

🔒 Is three.ws safe to install? View the security audit →

About three.ws

three.ws Website · X / Twitter · GitHub · $THREE on pump.fun https://github.com/user-attachments/assets/d52515d1-cb04-4dd6-98bd-fef233312dc4 Give your AI a body. three.ws is an open-source, browser-native 3D AI agent platform. Type a prompt and Forge generates a textured 3D model — or drop a GLB you already have. Add an LLM brain, register on-chain, and embed anywhere — no plugins, no server uploads, no installs required. Try it in 60 seconds: open three.ws/forge, type "a brass steampunk owl, full body", and download the GLB. Text→3D, image→3D, and sketch→3D — free draft tier, no account. Jump to the Forge section ↓ $THREE is the native token of the three.ws ecosystem — the one and only coin of the platform. Always verify the contract address above before trading. is the only token associated with three.ws. Table of Contents What is three.ws? Vision Roadmap [Key Features](#key-feature

3dai-agentanimationavatarblockchaincharacter-studioclaudeembeddingercgltf

Quick Facts

Stars98
Forks24
LanguageJavaScript
CategoryMCP Server
Quality Score55.9996801964043/100
Last Updated2026-08-19
Created2026-01-08
Platformsbrowser, claude-code, mcp, node
Est. Tokens~41421k

three.ws alternative? Top 6 similar tools

Looking for a three.ws alternative? If you're comparing three.ws 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.

  • noobot by xiayu1987 · ⭐ 146

    Cheapest Money-Saving Self-hosted AI agent workspace with tool calling, MCP, multi-model routing, sandboxed ex

  • cesium-mcp by gaopengbin · ⭐ 136

    Protocol-agnostic CesiumJS AI control runtime for MCP, WebMCP, function calling, and browser agents.

  • beacon-skill by Scottcjn · ⭐ 224

    Beacon - agent-to-agent pings with optional RTC value attached (BoTTube/Moltbook/RustChain + UDP bus)

  • claude-historian-mcp by Vvkmnn · ⭐ 177

    📜 An MCP server for conversation history search and retrieval in Claude Code

  • editor-mcp-server by playcanvas · ⭐ 135

    MCP Server for AI automation of the PlayCanvas Editor

  • vscode-mcp by tjx666 · ⭐ 97

    MCP server for Claude Code/VSCode/Cursor/Windsurf to use editor self functionality. ⚡ Get real-time LSP diagno

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular JavaScript Agent Tools

Frequently Asked Questions

What is three.ws?

three.ws is 3D AI agent platform for the browser. Load any GLB/glTF avatar, give it an LLM brain with memory, emotions, and tool use, then embed it anywhere as a web component. Includes a character studio, on-cha. It is categorized as a MCP Server with 98 GitHub stars.

What programming language is three.ws written in?

three.ws is primarily written in JavaScript. It covers topics such as 3d, ai-agent, animation.

How do I install or use three.ws?

You can find installation instructions and usage details in the three.ws GitHub repository at github.com/nirholas/three.ws. The project has 98 stars and 24 forks, indicating an active community.

What are the best alternatives to three.ws?

The top alternatives to three.ws on Agent Skills Hub include noobot, cesium-mcp, beacon-skill. 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