vision-mcp-worker
Provides image description using Cloudflare Workers AI vision models (e.g., Meta Llama 3.2 11B Vision).
Supports local vision models through the OpenAI-compatible API (e.g., Ollama) for image description.
Supports vision models through OpenAI-compatible chat completions APIs, allowing image description via OpenAI and similar providers.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@vision-mcp-workerWhat's in this image?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
vision-mcp-worker
部署在 Cloudflare Worker 上的 MCP 服务器,给 AI 提供"看图"能力(describe_image 工具),附带一个果味模型状态展示页。
MCP 端点:
https://<your-domain>/mcp(Streamable HTTP,建议用 Cloudflare Access Service Auth 保护)状态页:
https://<your-domain>/(模型与健康状态一览)详细接入文档:见 MCP_SETUP.md
部署配置模板:见 wrangler.toml.example(真实
wrangler.toml不提交)
模型配置与切换(环境变量)
模型完全通过环境变量配置,不用改代码。 修改后 pnpm run deploy 生效。
1. Workers AI 模型(默认,免费额度)
在 wrangler.toml 的 [vars] 里设置 VISION_MODEL:
[vars]
VISION_MODEL = "@cf/meta/llama-3.2-11b-vision-instruct"默认回退模型为 Meta Llama 3.2 11B Vision(稳定、抠文字/数字细节强、便宜)。
2. 第三方 OpenAI 兼容模型(可选,优先于 Workers AI)
任意 OpenAI 兼容的视觉模型提供商(OpenAI / DeepSeek / 智谱 / 中转站 / Ollama 等):
[vars]
OPENAI_API_BASE = "https://api.example.com/v1" # 提供商 OpenAI 兼容端点
OPENAI_API_MODEL = "gpt-4o-mini" # 第三方模型名(不填则复用 VISION_MODEL)# API Key 用 secret 存,不要写进仓库:
npx wrangler secret put OPENAI_API_KEY优先级:配置了 OPENAI_API_BASE + OPENAI_API_KEY → 走第三方(chat/completions,图片以 image_url 传入);否则走 Workers AI 的 VISION_MODEL。
3. 切换示例
想要的效果 | 配置 |
用 Workers AI 的 llama(回退默认) |
|
用第三方模型 | 设置 |
换其他第三方模型 | 改 |
注意事项
OPENAI_API_KEY是 secret,存于 Cloudflare(wrangler secret),状态页只显示"已配置/未配置"第三方中转若不稳定,健康检查会如实显示
DEGRADED,属正常现象多模态模型才能做图片识别;纯文本模型(如
kimi-k2系列)不能用于describe_image
Related MCP server: Cloudflare Image MCP
开发
pnpm install # 依赖
pnpm run deploy # 部署到 Cloudflare
pnpm test # 测试目录
文件 | 说明 |
| Worker 入口:MCP 端点 / 状态页 / 健康检查 / 模型路由 |
| 部署配置模板(真实配置见本地 |
| 本地截图识别脚本 |
| 测试页(仪表盘) |
| 完整接入与排障文档 |
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- Flicense-qualityCmaintenanceDeployable MCP server on Cloudflare Workers without authentication, enabling AI agents to use custom tools via SSE endpoint. Supports connection to Cloudflare AI Playground and local clients like Claude Desktop.Last updated
- Flicense-qualityBmaintenanceImage generation MCP server running on Cloudflare Workers, supporting multiple models like FLUX and SDXL with OpenAI-compatible endpoints.Last updated
- Flicense-qualityCmaintenanceA remote MCP server deployed on Cloudflare Workers without authentication, enabling integration with AI clients like Claude Desktop and Cloudflare AI Playground for tool execution.Last updated
- Flicense-qualityCmaintenanceA remote MCP server deployed on Cloudflare Workers for hosting and exposing MCP tools to AI clients via a remote endpoint.Last updated
Related MCP Connectors
MCP server for AI agents to plan, verify, and deploy Cloudflare-native apps.
Hosted MCP server connecting claude.ai, ChatGPT and other AI apps to your own computer
Cloud-hosted MCP server for durable AI memory
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/xanzl/cf-vision-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server