Vision Bridge
FreeNot checkedA universal vision MCP server that enables Claude Code and Claude Desktop to describe images, extract text, and answer questions about images by converting visu
About
A universal vision MCP server that enables Claude Code and Claude Desktop to describe images, extract text, and answer questions about images by converting visual content to text via multiple AI providers.
README
通用视觉 MCP 服务器,支持多种多模态 API 格式。当 Claude Code / Claude Desktop 使用的模型无法直接处理图片时,可通过该 MCP 工具将图片内容转换为文字描述,从而间接“看懂”图片。
功能
提供 3 个 MCP 工具:
describe_image:详细描述图片内容(对象、场景、文字、人物动作、颜色、布局等)。extract_image_text:提取图片中的所有文字(OCR)。ask_about_image:针对图片回答具体问题。
支持四种图片输入方式:
image_url:图片 URLimage_path:本地图片路径image_base64:Base64 编码的图片数据image:Messages API 格式的图片内容块,例如:
{
"type": "image",
"source": {
"type": "base64",
"media_type": "image/png",
"data": "iVBORw0KGgo..."
}
}
支持的 API 格式(Provider)
| Provider | 说明 | 默认 Endpoint |
|---|---|---|
anthropic |
Anthropic Messages API | /v1/messages |
openai |
OpenAI Chat Completions API | /chat/completions |
gemini |
Gemini Native generateContent API | /v1beta/models/{model}:generateContent |
通过 PROVIDER 环境变量切换 API 格式。
快速开始
全局安装
npm install -g @shen866/vision-bridge-mcp
本地开发
git clone https://github.com/shen866/vision-bridge-mcp.git
cd vision-bridge-mcp
npm install
npm run build
配置 Claude Code
API_KEY、BASE_URL、MODEL 为必填项。
Anthropic Messages
{
"mcpServers": {
"vision_bridge": {
"command": "npx",
"args": ["-y", "@shen866/vision-bridge-mcp"],
"env": {
"API_KEY": "your-api-key",
"BASE_URL": "https://api.anthropic.com",
"MODEL": "claude-3-5-sonnet-20241022"
}
}
}
}
如果使用本地构建版本,将 command 改为 node 并把 args 改为绝对路径:
{
"mcpServers": {
"vision_bridge": {
"command": "node",
"args": ["/Users/shen/workspace/kimi-vision-mcp/dist/index.js"],
"env": {
"API_KEY": "your-api-key",
"BASE_URL": "https://api.anthropic.com",
"MODEL": "claude-3-5-sonnet-20241022"
}
}
}
}
OpenAI Chat Completions
{
"mcpServers": {
"vision_bridge": {
"command": "npx",
"args": ["-y", "@shen866/vision-bridge-mcp"],
"env": {
"PROVIDER": "openai",
"API_KEY": "your-api-key",
"BASE_URL": "https://api.openai.com/v1",
"MODEL": "gpt-4o"
}
}
}
}
Gemini Native generateContent
{
"mcpServers": {
"vision_bridge": {
"command": "npx",
"args": ["-y", "@shen866/vision-bridge-mcp"],
"env": {
"PROVIDER": "gemini",
"API_KEY": "your-api-key",
"BASE_URL": "https://generativelanguage.googleapis.com",
"MODEL": "gemini-1.5-pro-latest"
}
}
}
}
使用
在 Claude Code / Claude Desktop 中发送图片或引用图片路径后,Claude 会自动调用 describe_image 等工具获取多模态模型对图片的文字描述,然后将描述交给纯文本模型继续处理。
如果 Claude Code 经常直接把图片发给模型导致报错,可以在项目根目录创建 .claude/CLAUDE.md:
当前模型不支持图片输入。当用户发送图片时,必须调用 vision_bridge MCP 工具处理,不要直接传给模型。
环境变量
| 变量 | 说明 | 默认值 |
|---|---|---|
PROVIDER |
API 格式:anthropic、openai、gemini |
anthropic |
API_KEY |
API 密钥 | 必填 |
BASE_URL |
API 基础地址 | 必填 |
ENDPOINT |
API 端点路径 | 取决于 provider |
MODEL |
模型名称 | 必填 |
MAX_TOKENS |
最大输出 token 数 | 4096 |
API_VERSION |
Messages API 版本 | 2023-06-01 |
AUTH_HEADER |
Messages API 认证方式:x-api-key 或 bearer |
x-api-key |
协议
基于 MCP(Model Context Protocol)JSON-RPC 2.0,通过 stdio 进行通信。
401 排查
如果返回 401,通常是认证头不对。各 provider 默认认证方式如下:
anthropic:x-api-key+anthropic-versionopenai:Authorization: Bearergemini:URL query parameter?key=
如果 Messages API 网关需要 Bearer Token,可设置:
"AUTH_HEADER": "bearer"
Install Vision Bridge in Claude Desktop, Claude Code & Cursor
unyly install vision-bridge-mcpInstalls into Claude Desktop, Claude Code, Cursor & VS Code — handles npx, uvx and build-from-source repos for you.
First time? Get the CLI: curl -fsSL https://unyly.org/install | sh
Or configure manually
Run in your terminal:
claude mcp add vision-bridge-mcp -- npx -y @shen866/vision-bridge-mcpFAQ
Is Vision Bridge MCP free?
Yes, Vision Bridge MCP is free — one-click install via Unyly at no cost.
Does Vision Bridge need an API key?
No, Vision Bridge runs without API keys or environment variables.
Is Vision Bridge hosted or self-hosted?
A hosted option is available: Unyly runs the server in the cloud, no local setup required.
How do I install Vision Bridge in Claude Desktop, Claude Code or Cursor?
Open Vision Bridge on unyly.org, pick your client tab (Claude Desktop, Claude Code, Cursor) and press Install — the config is generated automatically, no JSON editing.
Related MCPs
GitHub
PRs, issues, code search, CI status
by GitHubFilesystem
Secure file operations with configurable access controls.
Memory
Knowledge graph-based persistent memory system.
Template MCP Server
A CLI tool to create a new Model Context Protocol server project with TypeScript support, dual transport options, and an extensible structure
by mcpdotdirectCompare Vision Bridge with
Not sure what to pick?
Find your stack in 60 seconds
Author?
Embed badge for your README
Browse similar
All development MCPs
