Skip to main content

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

安装方式一:通过 PyPI / uvx 使用(推荐)

MCP 配置示例:

{
  "mcpServers": {
    "visual-understand": {
      "command": "uvx",
      "args": ["visual-understand-mcp"],
      "env": {
        "VISION_API_BASE": "https://dashscope.aliyuncs.com/compatible-mode/v1",
        "VISION_MODEL": "qwen-vl-max",
        "VISION_API_KEY": "sk-xxx"
      }
    }
  }
}

安装方式二:本地源码运行

{
  "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"
      }
    }
  }
}

配置项

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 见下方

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。

默认系统提示词:

你是一个图片分析助手,仅用于理解图片内容。请按以下结构分析图片,根据实际内容调整详细程度:1. 文字内容 — 逐字提取图中所有可见文字,保留原始格式和层级关系。2. 错误信息与代码 — 如果图中包含错误信息或代码片段,必须原样输出,不做任何改写或概括;如果没有则忽略此项。3. 视觉布局与元素 — 描述空间排列、尺寸、颜色及关键元素间的关系。UI 截图请识别组件类型及其状态。4. 数据与指标 — 图表、表格请提取数值、坐标轴、标签、趋势及异常数据点。5. 整体概述 — 概括图片的主题、场景和关键信息,提供完整的上下文理解。不适用的部分跳过。只描述图片中可见的内容,不做推理、猜测或延伸解读。保持精确客观,不推测不可见的内容。

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

Metadata

Release files for visual-understand-mcp 0.1.2

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for visual-understand-mcp 0.1.2
File Size Uploaded Provenance
visual_understand_mcp-0.1.2.tar.gz 64.3 kB Without provenance Details

Built distribution (wheel)

Table of built distributions (wheels) for visual-understand-mcp 0.1.2
File Interpreter ABI Platform
visual_understand_mcp-0.1.2-py3-none-any.whl Python 3 none any Details

Total release size: 71.9 kB

Release files / visual_understand_mcp-0.1.2.tar.gz

Download URL visual_understand_mcp-0.1.2.tar.gz
Size 64.3 kB
Tags Source
SHA-256 checksum
How to use checksums
42188228821db1248752405aa9652993bf8a0e52da4c6e5faa8c52d19be09e14
BLAKE2b-256 checksum
How to use checksums
86b66e4261843f36796645657c9f49d2abc1caf8d3e853fd357041e6112e22ba
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.2.0 CPython/3.10.17

Release files / visual_understand_mcp-0.1.2-py3-none-any.whl

Download URL visual_understand_mcp-0.1.2-py3-none-any.whl
Size 7.6 kB
Tags Python 3
SHA-256 checksum
How to use checksums
942249711b44b6120e7e256387ffc1c86e74086a61f22b426ce4b09af7ecdd37
BLAKE2b-256 checksum
How to use checksums
2f9a2d110d06da03b8d38d26fdcc3a06d28e569980205fb4bf30c037d282bfb8
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.2.0 CPython/3.10.17

Security for visual-understand-mcp 0.1.2

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page