视觉理解 MCP Server - 为不支持视觉的编码模型提供图片理解能力
Project description
视觉理解 MCP Server
为不支持视觉的编码模型提供图片理解能力。
原理
编码模型(如 GLM-5.1)遇到图片时,自动调用 MCP 工具 understand_image,由视觉模型完成图片识别,结果以文本回传给编码模型继续推理。无需切换模型,上下文不中断。
用户粘贴截图 → 编码模型调用 understand_image → 视觉模型识别 → 文字描述回传 → 继续编码
配置
在 MCP 客户端配置中通过 env 传入:
{
"mcpServers": {
"visual-understand": {
"command": "uv",
"args": [
"--directory", "/path/to/visual-understand-mcp",
"run", "visual-understand-mcp"
],
"env": {
"VISION_API_BASE": "https://dashscope.aliyuncs.com/compatible-mode/v1",
"VISION_MODEL": "qwen-vl-max",
"VISION_API_KEY": "sk-xxx"
}
}
}
}
| 变量 | 说明 | 默认值 |
|---|---|---|
VISION_API_BASE |
视觉模型 API 地址 | 无(必填) |
VISION_MODEL |
视觉模型名称 | 无(必填) |
VISION_API_KEY |
视觉模型密钥 | 无(必填) |
VISION_TEMPERATURE |
输出随机性 | 0.1 |
VISION_MAX_TOKENS |
最大输出长度 | 12000 |
VISION_TIMEOUT |
请求超时(秒) | 120 |
VISION_SYSTEM_PROMPT |
视觉模型系统提示词 | 见上 |
前三个必填,其余可选。配置也可写入
~/.visual-understand-mcp/config.json,env 优先级更高。
建议写入 CLAUDE.md
进行图片识别任务时,使用 visual-understand MCP 的 understand_image 工具。
本地调试
uv run mcp dev src/visual_understand_mcp/server.py
License
MIT
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
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 visual_understand_mcp-0.1.0.tar.gz.
File metadata
- Download URL: visual_understand_mcp-0.1.0.tar.gz
- Upload date:
- Size: 64.2 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.10.17
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
806094b0c4e0f301f80bce668b5ed2397f25a18431faa9880aecd09f08fe472d
|
|
| MD5 |
907472f16158fea6807447f88aaed159
|
|
| BLAKE2b-256 |
4983d63350ae028f015e3ae629d272655deed0c9558d3c3ce12ff59651635536
|
File details
Details for the file visual_understand_mcp-0.1.0-py3-none-any.whl.
File metadata
- Download URL: visual_understand_mcp-0.1.0-py3-none-any.whl
- Upload date:
- Size: 7.2 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.10.17
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
daeb2c14fc42bb6381aeb60d740aa440b4a0d2c2f1662ce5a7df93ead2203a0d
|
|
| MD5 |
c427cf838450cba396e70809f94b6e24
|
|
| BLAKE2b-256 |
5f7aa885c0567d822163813f69942f7eb761a67bbd9b5fb69e7459b813d102e7
|