
该工具已被弃用。请使用代理文档提取(Agentic Document Extraction)。
概览
该项目在v1.0之前可能会有重大变更。 现代LLM“代理”通过一个轻量级的副车MCP服务器调用外部工具,服务器本地运行于STDIN/STDOUT,将MCP兼容客户端(Claude Desktop、Cursor、Cline等)的每次工具调用转换为对Landing AI的VisionAgent REST API的认证HTTPS请求。响应JSON以及任何图像或掩码都会被流回模型,这样你就可以在编辑器中发布自然语言的计算机视觉和文档分析命令,而无需编写自定义REST代码或加载额外SDK。 https://github.com/user-attachments/assets/2017fa01-0e7f-411c-a417-9f79562627b7 每当 VisionAgent 发布新端点时运行。脚本获取最新的 OpenAPI 规范并自动重新生成本地工具映射。 如果您没有 VisionAgent API 密钥,请创建账户并获取您的 API 密钥。 3. 打开你的MCP感知客户端。4. 下载街道。
概述(AI 翻译)
Beta – v0.1 该项目处于抢先体验阶段,且在v1.0之前可能会有破坏性变更。
VisionAgent MCP 服务器 v0.1 - 概述
现代LLM“代理”通过**Model Context协议(MCP)调用外部工具。VisionAgent MCP 是一个轻量级的副车MCP服务器,运行在本地STDIN/STDOUT上,将兼容MCP客户端(Claude Desktop、Cursor、Cline等)的每个工具调用转换为认证的HTTPS请求,发送给Landing AI的VisionAgent REST API。响应的JSON以及任何图像或掩码都会被流回模型,这样你就可以从编辑器中发布自然语言计算机视觉和文档分析命令,而无需编写自定义REST代码或加载额外的SDK。
📸 演示
https://github.com/user-attachments/assets/2017fa01-0e7f-411c-a417-9f79562627b7
🧰 支持的使用场景(v0.1)
| 能力 | 描述 |
|---|---|
agentic-document-analysis |
解析PDF/图片以提取文本、表格、图表和图表,考虑布局和其他视觉线索。 |
本页由 AI 翻译,技术细节请以原文为准。
README
以下为原文 README 节选,完整内容请查看原文。
VisionAgent MCP Server
Beta – v0.1
This project is early access and subject to breaking changes until v1.0.
VisionAgent MCP Server v0.1 - Overview
Modern LLM “agents” call external tools through the Model Context Protocol (MCP). VisionAgent MCP is a lightweight, side-car MCP server that runs locally on STDIN/STDOUT, translating each tool call from an MCP-compatible client (Claude Desktop, Cursor, Cline, etc.) into an authenticated HTTPS request to Landing AI’s VisionAgent REST APIs. The response JSON, plus any images or masks, is streamed back to the model so that you can issue natural-language computer-vision and document-analysis commands from your editor without writing custom REST code or loading an extra SDK.
📸 Demo
https://github.com/user-attachments/assets/2017fa01-0e7f-411c-a417-9f79562627b7
🧰 Supported Use Cases (v0.1)
| Capability | Description |
|---|---|
agentic-document-analysis |
Parse PDFs / images to extract text, tables, charts, and diagrams taking into account layouts and other visual cues. Web Version here. |
text-to-object-detection |
Detect free-form prompts (“all traffic lights”) using OWLv2 / CountGD / Florence-2 / Agentic Object Detection (Web Version here); outputs bounding boxes. |
text-to-instance-segmentation |
Pixel-perfect masks via Florence-2 + Segment-Anything-v2 (SAM-2). |
activity-recognition |
Recognise multiple activities in video with start/end timestamps. |
depth-pro |
High-resolution monocular depth estimation for single images. |
Run
npm run generate-toolswhenever VisionAgent releases new endpoints. The script fetches the latest OpenAPI spec and regenerates the local tool map automatically.
🗺 Table of Contents
- Quick Start
- Configuration
- Example Prompts
- Architecture & Flow
- Developer Guide
- Troubleshooting
- Contributing
- Security & Privacy
🚀 Quick Start
Get Your VisionAgent API Key
安装
npx vision-tools-mcp配置
# 1 Install
npm install -g vision-tools-mcp
# 2 Configure your MCP client with the following settings:
{
"mcpServers": {
"VisionAgent": {
"command": "npx",
"args": ["vision-tools-mcp"],
"env": {
"VISION_AGENT_API_KEY": "<YOUR_API_KEY>",
"OUTPUT_DIRECTORY": "/path/to/output/directory",
"IMAGE_DISPLAY_ENABLED": "true" # or false, see below
}
}
}
}