three.ws Vision

io.github.nirholas由 GitHub 账号 nirholas 发布v0.1.2更新于 Oct 24, 2026

Image understanding for AI agents — analyze and describe any image via the three.ws pipeline.

已验证STDIO仅桌面媒体与设计AI 与机器学习

概览

AI 生成的概览

本地 stdio MCP 服务器，通过 three.ws 让助手具备图像理解能力：就图片提问、读取截图文字、生成替代文本。

可以做什么
  • 针对图片回答提示词：视觉问答、截图 OCR、分类或渲染图点评
  • 生成自然语言描述与替代文本，可按详细程度和关注点调整
  • 查询视觉服务是否在线以及支持哪些图片格式
  • 接受公开 https 图片链接或 base64 / data URI 输入
适用场景
当助手需要查看自己无法直接看到的图片时适用，例如读取截图中的文字、生成说明或替代文本、识别画面内容，或评审 3D 与虚拟形象渲染图。
运行要求
需要 Node.js 20 或更高版本，可通过 npx 或 npm 安装运行。需要能访问 three.ws 端点（或自定义 THREE_WS_BASE）。可选 THREE_WS_API_KEY 作为 bearer 令牌，以及 THREE_WS_TIMEOUT_MS；免费层无需密钥。图片须为 JPEG、PNG、WebP 或 GIF，最大 12 MB，imageUrl 必须是公开 https 地址。
安装前请注意
图片（包括 base64 内容）会发送到 three.ws 服务进行分析，请勿提交机密截图。请求按 IP 限流；可选的 THREE_WS_API_KEY 可提高限额，并以 bearer 令牌形式发送。工具为只读，但结果不确定，且后端模型链路可能变化。

安装

在 SourceWeft 中

  1. 打开 控制台中的 three.ws Vision，将其添加到工作区。
  2. 为需要使用其工具的对话启用该服务。

Desktop only，通过 STDIO。 STDIO 服务会启动本地进程，因此需要 SourceWeft 桌面宿主。

其他 MCP 客户端

参照 仓库 中的启动说明。

README

[three.ws]

@three-ws/vision-mcp

Let any AI agent see — analyze and describe images through the three.ws vision pipeline, free-first and no key required.

[npm] [license] [node] [MCP Registry] [three.ws]

A Model Context Protocol server that gives any AI assistant image understanding over stdio. Pass an image as a public URL or base64 and the agent can read the text in a screenshot, identify what's in a scene, critique a 3D/avatar render, or write alt-text — all live, read-only, no key required.

Every answer comes from the three.ws vision pipeline: free NVIDIA NIM vision models lead every request, with an automatic server-side paid backstop behind them. The caller never pays and needs no provider key — point THREE_WS_BASE at a deployment and go.

Install

bash
npm install @three-ws/vision-mcp

Or run with npx (no install):

bash
npx @three-ws/vision-mcp

Quick start

Claude Code, one line:

bash
claude mcp add vision -- npx -y @three-ws/vision-mcp

Claude Desktop / Cursor (claude_desktop_config.json or mcp.json):

json
{	"mcpServers": {		"vision": {			"command": "npx",			"args": ["-y", "@three-ws/vision-mcp"]		}	}}

Inspect the surface with the MCP Inspector:

bash
npx -y @modelcontextprotocol/inspector npx @three-ws/vision-mcp

Tools

ToolTypeWhat it does
analyze_imageread-onlyAnswer a prompt about an image — visual Q&A, OCR (read a screenshot), classification, or critiquing a render.
describe_imageread-onlyNatural-language description for alt text or a caption, steerable by detail level and focus.
get_vision_statusread-onlyReport whether a vision provider is live and which image formats are accepted. No image, no cost.

All three tools are read-only — they look at an image, they never store or mutate anything. A VLM is non-deterministic and the live provider chain moves, so none are idempotent.

Input parameters

analyze_image — prompt (required), and exactly one of imageUrl (public https) or image (base64 / data URI). Optional imageType (for raw base64), maxTokens (16–2048, default 512).

describe_image — exactly one of imageUrl or image. Optional imageType, detail (brief | standard | detailed, default standard), focus (an aspect to emphasize).

get_vision_status — no parameters.

Example

jsonc
// analyze_image: read the text in a logo image> { "imageUrl": "https://three.ws/logo.png", "prompt": "What does this logo say?" }{  "ok": true,  "text": "The logo reads \"three.ws\".",  "provider": "nvidia",  "model": "nvidia/nemotron-nano-12b-v2-vl",  "prompt": "What does this logo say?",  "image_source": "url"}
jsonc
// describe_image — alt text from a base64 image> { "image": "data:image/png;base64,iVBORw0KG...", "detail": "brief" }{  "ok": true,  "description": "A seagull in profile against a blurred coastal background.",  "detail": "brief",  "provider": "nvidia",  "model": "nvidia/nemotron-nano-12b-v2-vl",  "image_source": "base64"}
jsonc
// get_vision_status — gate a "describe this" affordance> {}{  "ok": true,  "configured": true,  "image_types": ["image/jpeg", "image/png", "image/webp", "image/gif"],  "max_image_mb": 12}

Examples

Runnable, key-free examples live in examples/:

bash
node examples/list-tools.mjs     # every tool with its full input schemanode examples/read-an-image.mjs  # status + alt text + OCR on a live image

Both spawn this server over stdio and call the real vision pipeline. Every tool is read-only, so nothing is stored and nothing is paid. See examples/README.md for expected output.

Images may be JPEG, PNG, WebP, or GIF, up to 12 MB. Base64 inputs are size-checked locally before upload; imageUrl must be a public https URL (the vision server fetches it, so private/loopback hosts are rejected).

Pricing & auth

There is no charge to the caller and no key is needed. The platform runs every request against free NVIDIA NIM vision lanes first and falls back to a paid model only on its own infrastructure — that cost is the platform's, transparent to you.

The endpoint is rate-limited per IP. To raise your limit to the per-user tier, set the optional THREE_WS_API_KEY (a three.ws API key); it is sent as a bearer token. It is never required to use the free model.

Requirements

  • Node.js >= 20.
  • Network access to https://three.ws (or your own THREE_WS_BASE).

Environment variables

VariableRequiredDefaultPurpose
THREE_WS_BASEnohttps://three.wsWhich deployment to call.
THREE_WS_TIMEOUT_MSno30000Per-request timeout (a call may chain across free lanes).
THREE_WS_API_KEYno—Optional bearer token to raise the rate limit to per-user.

Links

Part of the three.ws SDK suite — 3D AI agents, on-chain identity, and agent payments.
Website · Changelog · GitHub

来源：packages/vision-mcp/README.md，提交 c8f2cde

工具

0
SourceWeft 尚未在沙箱中启动过该软件包，因此其工具未知。

版本历史

2
  1. v0.1.2最新Oct 10, 2026
  2. v0.1.1Sep 16, 2026

评分

已满足适用检查项的 50%

该评分衡量此收录条目的完整程度，依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价，也不表示服务器安全或当前可用：可连通性是带日期的检查结果，评分也不包含安装量或用户评价。

  • 近 30 天内可连通25 分

    请保持端点能够响应 MCP 握手；SourceWeft 每 30 天探测一次。

  • 已声明认证方式10 分

    请在注册中心条目中声明凭据请求头，或保持端点能够响应探测，以便判定其认证方式。

  • 已列出工具15 分

    请让服务器在无凭据时响应 tools/list，或发布可在沙箱中无凭据启动的软件包。

  • 描述必需15 分
  • 图标10 分
  • 文档15 分
  • 许可证10 分