Skip to main content
Glama
Sign In
vision-mcp

vision-mcp

by sunqb
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

vision-mcp

图像理解 MCP Server(stdio 形式),对标 z.ai vision-mcp-server,底层经 OpenAI 兼容接口调用视觉模型(支持火山方舟 ARK 等 provider,默认 doubao-seed-2.0-code)。

工具一览

共 7 个图像工具(未实现 video_analysis):

工具

说明

image_analysis

通用图像理解

extract_text_from_screenshot

截图 OCR,提取代码/终端/文档/普通文本

diagnose_error_screenshot

分析错误截图,给可操作修复建议

understand_technical_diagram

解读架构图/流程图/UML/ER 图等

analyze_data_visualization

读取图表/仪表盘,提取洞察与趋势

ui_to_artifact

UI 截图转代码/提示词/规格说明/描述

ui_diff_check

比较两张 UI 截图差异

图片输入统一支持三种形式:本地路径、HTTP(S) URL、data:image/...;base64,... URI。 URL 与本地路径都会先在本地下载/读取并转 base64,以 data URI 内联发送,规避模型后端拉取外网图片超时。

Related MCP server: SiliconFlow-Vision-MCP

配置

通过环境变量配置后端服务:

环境变量

说明

默认值

OLLAMA_BASE_URL

OpenAI 兼容服务根地址

http://localhost:11434

OLLAMA_API_KEY

Bearer 鉴权密钥

(空)

OLLAMA_MODEL

视觉模型名

doubao-seed-2.0-code

变量名仍沿用 OLLAMA_* 以保持向后兼容,实际已不依赖 Ollama 原生接口, 而是走标准 OpenAI /chat/completions。

安装

需 Python ≥ 3.10 与 uv。

cd 识图mcp
uv sync          # 安装依赖
uv run vision-mcp --help        # 验证可运行

客户端配置

Claude Desktop / Cline / Roo Code

{
  "mcpServers": {
    "vision-mcp": {
      "type": "stdio",
      "command": "uv",
      "args": ["run", "--directory", "/Volumes/samsungssd/code/temp/识图mcp", "vision-mcp"],
      "env": {
        "OLLAMA_BASE_URL": "https://ark.cn-beijing.volces.com/api/coding/v3",
        "OLLAMA_API_KEY": "你的ARK_API_KEY",
        "OLLAMA_MODEL": "doubao-seed-2.0-code"
      }
    }
  }
}

ZCode

{
  "mcpServers": {
    "vision-mcp": {
      "command": "uv",
      "args": ["run", "--directory", "/Volumes/samsungssd/code/temp/识图mcp", "vision-mcp"],
      "env": {
        "OLLAMA_BASE_URL": "https://ark.cn-beijing.volces.com/api/coding/v3",
        "OLLAMA_API_KEY": "你的ARK_API_KEY",
        "OLLAMA_MODEL": "doubao-seed-2.0-code"
      }
    }
  }
}

提示:--directory 指向本项目的绝对路径,请按实际位置修改。也可用 uvx --from /path/to/识图mcp vision-mcp。

使用示例

在客户端对话中直接提到图片路径/URL 即可,例如:

  • "这张图 demo.png 里有什么?" → 触发 image_analysis

  • "提取这张终端报错截图的文本" → 触发 extract_text_from_screenshot

  • "对比 v1.png 和 v2.png 两个界面的差异" → 触发 ui_diff_check

开发与测试

uv sync
# 直接以 stdio 模式运行(可用 MCP inspector / 客户端连接)
uv run vision-mcp

Available Tools

7 tools
analyze_data_visualizationA

读取数据可视化图表(柱状/折线/饼图、仪表盘等),提取洞察与趋势。

Args: image: 图表图片(路径 / URL / base64 URI)。 question: 可选,关注的指标或问题。

Inputs: image (required), question. Returns: result

diagnose_error_screenshotA

分析错误/异常截图,定位问题并给出可操作的修复建议。

Args: image: 错误截图(路径 / URL / base64 URI)。 context: 可选,补充背景,如相关代码、操作步骤、环境信息等。

Inputs: image (required), context. Returns: result

extract_text_from_screenshotA

对截图进行 OCR,提取其中的文本。适用于代码、终端输出、文档、普通文本等。

Args: image: 图片输入(路径 / URL / base64 URI)。 question: 可选,特定提取要求,如"只提取报错堆栈"。

Inputs: image (required), question. Returns: result

image_analysisA

通用图像理解。适用于其他专用工具不匹配的场景。

Args: image: 图片输入,支持本地路径 / HTTP(S) URL / data:image base64 URI。 question: 想了解的内容或问题。

Inputs: image (required), question (required). Returns: result

ui_diff_checkA

比较两张 UI 截图,标记视觉或实现上的差异。

Args: image1: 第一张截图(路径 / URL / base64 URI)。 image2: 第二张截图(路径 / URL / base64 URI)。 question: 可选,关注的具体差异点。

Inputs: image1 (required), image2 (required), question. Returns: result

ui_to_artifactA

将 UI 截图转换为指定产物:代码、提示词、规格说明或描述。

Args: image: UI 截图(路径 / URL / base64 URI)。 target_type: 目标产物类型,可选:code(前端代码)、prompt(复刻用提示词)、 specification(规格说明)、description(文字描述)。 question: 可选,额外要求,如"用 React + Tailwind""响应式"。

Inputs: image (required), target_type (required), question. Returns: result

understand_technical_diagramA

解读技术图表,如架构图、流程图、UML、ER 图、系统设计图等。

Args: image: 图表图片(路径 / URL / base64 URI)。 question: 可选,想了解的具体方面。

Inputs: image (required), question. Returns: result

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Deploy Server
    One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

    TDQS

    A3.9/5.0

    Scored across 7 tools

    Disambiguation4/5

    The specialized tools (OCR, error diagnosis, diagrams, data viz, UI conversion, UI diff) have distinct purposes, and the generic image_analysis is explicitly positioned as a fallback. However, understand_technical_diagram and analyze_data_visualization could overlap for certain images, and image_analysis could be used for any task, creating some ambiguity.

    Naming Consistency3/5

    Most tools follow a verb_object pattern (extract_text_from_screenshot, diagnose_error_screenshot, understand_technical_diagram, analyze_data_visualization), but image_analysis is noun-based and ui_to_artifact is not verb-first. ui_diff_check is also ambiguous in word order, so the pattern is mixed but still readable.

    Tool Count5/5

    Seven tools is a well-scoped number for a vision MCP server. It covers a broad range of image analysis tasks without being bloated, and each tool has a clear role.

    Completeness4/5

    The tool set covers major vision tasks: generic understanding, OCR, error screenshot diagnosis, technical diagram interpretation, data visualization analysis, UI conversion, and UI diff checking. Minor gaps exist, such as no generic image comparison (only UI-specific) and no image generation/transformation, but these are somewhat outside the core analysis purpose.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Resources

    Related MCP Connectors

    Related MCP Servers