Skip to main content

VL 视觉理解 MCP 服务 - 基于 tokendance 的 Qwen2.5-VL 模型

Project description

VL MCP Server

基于 MCP(Model Context Protocol)协议的视觉理解服务,通过 tokendance 平台调用 Qwen2.5-VL 模型,实现图片内容分析功能。

功能特性

  • 支持图片 URL 和 Base64 编码输入
  • 基于 Qwen2.5-VL-7B-Instruct 模型
  • 兼容 Cherry Studio、Claude Code、Cursor 等 MCP 客户端
  • 可托管部署到魔搭 MCP 广场

安装使用

环境要求

  • Python >= 3.10
  • uv(推荐)或 pip

配置

设置环境变量:

export TOKENDANCE_API_KEY="your-api-key"

MCP 客户端配置

Cherry Studio / Claude Desktop / Cursor:

{
  "mcpServers": {
    "vl-image-analyzer": {
      "command": "uvx",
      "args": ["vl-mcp-server"],
      "env": {
        "TOKENDANCE_API_KEY": "your-api-key"
      }
    }
  }
}

开发

本地开发

# 克隆仓库
git clone <repo-url>
cd vl-mcp-server

# 使用 uv 安装依赖
uv sync

# 运行服务
uv run vl-mcp-server

调试

使用 MCP Inspector:

npx @modelcontextprotocol/inspector uv run vl-mcp-server

工具说明

analyze_image

分析图片内容并返回描述。

参数:

  • image (string, 必填): 图片 URL 或 Base64 编码字符串
  • image_type (string, 可选): 图片类型,"url" 或 "base64",默认 "url"
  • prompt (string, 可选): 自定义分析提示词,默认 "请详细描述这张图片的内容"

示例:

{
  "image": "https://example.com/image.jpg",
  "image_type": "url",
  "prompt": "描述这张图片的主要内容"
}

许可证

MIT License

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

vl_mcp_server-0.1.0.tar.gz (45.6 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

vl_mcp_server-0.1.0-py3-none-any.whl (4.8 kB view details)

Uploaded Python 3

File details

Details for the file vl_mcp_server-0.1.0.tar.gz.

File metadata

  • Download URL: vl_mcp_server-0.1.0.tar.gz
  • Upload date:
  • Size: 45.6 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.6.11

File hashes

Hashes for vl_mcp_server-0.1.0.tar.gz
Algorithm Hash digest
SHA256 7ff432fe06828443ce0d1b2fbd5be38b931bdf34af7d6a3d9968be39d23310c3
MD5 994af11d0b9ccf9dbb69bbeeec71ea22
BLAKE2b-256 350ef805b8cb9ec90ec258fd241154a76e4e759b82bb99069e66f0dc82b3b252

See more details on using hashes here.

File details

Details for the file vl_mcp_server-0.1.0-py3-none-any.whl.

File metadata

File hashes

Hashes for vl_mcp_server-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 0d1ad9c512d93e73bf86d612ae2fd26c83456682ca31221885badbf3b5fd2cdb
MD5 7d313a97acb757225ca2f3bc06ae20bf
BLAKE2b-256 764ee815af86d698efc59315722f6d0fc920f8e906b60e806777062f84036212

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page