VLM Image Understanding MCP Server - Support OpenAI protocol compatible VLMs
Project description
VLM MCP Server
支持 OpenAI 协议兼容的 VLM 图片理解 MCP Server。
功能
- extract_text_from_image: 从图片中提取文字 (OCR)
- ui_to_artifact: 将 UI 截图转换为代码、提示词、设计规格或描述
- extract_text_from_screenshot: 从截图提取文本,支持代码识别
- diagnose_error_screenshot: 分析错误截图,诊断问题原因
- understand_technical_diagram: 分析技术图表(架构图、流程图、UML等)
- analyze_data_visualization: 分析数据可视化图表
- ui_diff_check: UI 对比检测,找出视觉差异
- analyze_image: 通用图片分析
环境变量
| 变量名 | 必填 | 说明 |
|---|---|---|
VLM_API_KEY |
是 | API 密钥 |
VLM_BASE_URL |
否 | 自定义 API 地址(默认: https://api.openai.com/v1) |
VLM_MODEL |
否 | 使用的模型(默认: gpt-4o) |
快速开始
使用 uvx 运行(推荐)
# 设置环境变量
export VLM_API_KEY=your-api-key
export VLM_MODEL=gpt-4o
# 直接运行
uvx vlm-mcp
使用 pip 安装
# 安装
pip install vlm-mcp
# 或开发模式安装
pip install -e .
配置环境变量
# OpenAI
export VLM_API_KEY=sk-xxx
export VLM_MODEL=gpt-4o
# 自定义 API (如 Ollama)
export VLM_API_KEY=your-api-key
export VLM_BASE_URL=http://localhost:11434/v1
export VLM_MODEL=qwen2.5-vl
运行服务
# 直接运行
python -m vlm_mcp
# 或使用安装的命令
vlm-mcp
支持的模型
任何兼容 OpenAI Chat Completions API 的 VLM 模型:
- gpt-4o
- gpt-4o-mini
- gpt-4-turbo
- qwen2.5-vl 系列
- 及其他兼容 OpenAI API 的模型
Claude Code 配置
在 Claude Code 中配置 MCP 服务器:
{
"mcpServers": {
"vlm-mcp": {
"command": "uvx",
"args": ["vlm-mcp"],
"env": {
"VLM_API_KEY": "your-api-key",
"VLM_MODEL": "gpt-4o"
}
}
}
}
使用示例
在 Claude Code 中使用:
请用 extract_text_from_image 工具分析这张图片 /path/to/image.jpg,提取其中的文字。
请用 ui_to_artifact 工具将这个UI截图转换为 React 代码。
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
vlm_mcp-0.1.0.tar.gz
(7.5 kB
view details)
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file vlm_mcp-0.1.0.tar.gz.
File metadata
- Download URL: vlm_mcp-0.1.0.tar.gz
- Upload date:
- Size: 7.5 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: uv/0.10.7 {"installer":{"name":"uv","version":"0.10.7","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
c821b7f888ef33e52f34db2e5a0fef5c5b033191beb02af97dbae38831ad5104
|
|
| MD5 |
c11735095bfc5716ad7c7c736fa0c826
|
|
| BLAKE2b-256 |
5f0db4602bf0b2b1cd0ce22d590ea395baab6e736e900c3b87a2440ffa2e4e6c
|
File details
Details for the file vlm_mcp-0.1.0-py3-none-any.whl.
File metadata
- Download URL: vlm_mcp-0.1.0-py3-none-any.whl
- Upload date:
- Size: 8.2 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: uv/0.10.7 {"installer":{"name":"uv","version":"0.10.7","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
ec8479e2e166247c5a6ac766ea226ffb376751c1b31dd46e26af2156eeb46f92
|
|
| MD5 |
7100b4427296eb683f20a57b482885b6
|
|
| BLAKE2b-256 |
94d09e39da7d55c52d1a1c221eae3ff3ab05c8026e00538eac11bd7ef379a49d
|