Skip to main content

MCP server for MIMO image recognition

Project description

MIMO Image Recognition MCP

一个调用小米 MIMO 多模态模型进行图片理解的 MCP Server。

该 MCP 支持:

  • 本地图片路径识别
  • 网络图片 URL 识别
  • Agent 自定义提示词
  • API Key、请求地址、模型名称通过 MCP 启动配置传入
  • 支持通过 PyPI / uvx 运行
  • 支持本地源码运行

功能说明

本项目会向 MCP 客户端暴露一个工具:

understand_image

用于调用 MIMO 多模态模型理解图片。

支持的输入方式:

  • image_path:本地图片路径,例如 E:/screenshot.png
  • image_url:网络图片 URL,例如 https://example.com/image.png
  • prompt:由 Agent 自己决定的图片理解任务
  • system_prompt:可选系统提示词
  • temperature:输出随机性
  • max_tokens:最大输出长度

安装方式一:通过 PyPI / uvx 使用

如果你只是想使用这个 MCP,推荐使用这种方式。

MCP 配置示例:

{
  "mcpServers": {
    "mimo-image-recognition": {
      "command": "uvx",
      "args": [
        "mimo-image-recognition-mcp"
      ],
      "env": {
        "MIMO_API_KEY": "你的 MIMO API Key",
        "MIMO_API_BASE": "https://api.xiaomimimo.com/v1",
        "MIMO_MODEL": "mimo-v2.5"
      }
    }
  }
}

配置项说明:

配置项 说明
MIMO_API_KEY 你的 MIMO API Key
MIMO_API_BASE MIMO API 请求地址,通常为 https://api.xiaomimimo.com/v1
MIMO_MODEL 要调用的 MIMO 模型名称,例如 mimo-v2.5

安装方式二:本地源码运行

如果你想修改源码或参与开发,可以使用本地源码方式。

1. 克隆项目

git clone https://github.com/Mrieatsc/mimo-image-recognition-mcp.git
cd mimo-image-recognition-mcp

2. 安装依赖

uv sync

3. MCP 配置示例

{
  "mcpServers": {
    "mimo-image-recognition": {
      "command": "uv",
      "args": [
        "--directory",
        "E:/mimo-image-recognition",
        "run",
        "mimo-image-recognition-mcp"
      ],
      "env": {
        "MIMO_API_KEY": "你的 MIMO API Key",
        "MIMO_API_BASE": "https://api.xiaomimimo.com/v1",
        "MIMO_MODEL": "mimo-v2.5"
      }
    }
  }
}

请把:

E:/mimo-image-recognition

改成你自己本地项目的真实路径。


本地调试

可以使用 MCP Inspector 调试:

uv run mcp dev src/mimo_image_recognition_mcp/server.py

如果能看到:

understand_image

说明 MCP Server 启动成功。

如果你想在 MCP Inspector 中实际调用 MIMO 接口,可以在当前终端临时设置:

Windows PowerShell

$env:MIMO_API_KEY="你的 MIMO API Key"
$env:MIMO_API_BASE="https://api.xiaomimimo.com/v1"
$env:MIMO_MODEL="mimo-v2.5"

uv run mcp dev src/mimo_image_recognition_mcp/server.py

License

MIT

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

mimo_image_recognition_mcp-0.1.1.tar.gz (51.8 kB view details)

Uploaded Source

Built Distribution

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

mimo_image_recognition_mcp-0.1.1-py3-none-any.whl (6.3 kB view details)

Uploaded Python 3

File details

Details for the file mimo_image_recognition_mcp-0.1.1.tar.gz.

File metadata

  • Download URL: mimo_image_recognition_mcp-0.1.1.tar.gz
  • Upload date:
  • Size: 51.8 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.11.7 {"installer":{"name":"uv","version":"0.11.7","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":null,"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}

File hashes

Hashes for mimo_image_recognition_mcp-0.1.1.tar.gz
Algorithm Hash digest
SHA256 f07111d5dc54e504edadccb780a5a86d729e1fc595a2e32aac72217667c641d2
MD5 595f57f240979378005af1a645715e1b
BLAKE2b-256 0d2cda415f1e1921ae6e76d09f338ab0eb0e303b75605bdd28bafcb50923ac99

See more details on using hashes here.

File details

Details for the file mimo_image_recognition_mcp-0.1.1-py3-none-any.whl.

File metadata

  • Download URL: mimo_image_recognition_mcp-0.1.1-py3-none-any.whl
  • Upload date:
  • Size: 6.3 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.11.7 {"installer":{"name":"uv","version":"0.11.7","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":null,"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}

File hashes

Hashes for mimo_image_recognition_mcp-0.1.1-py3-none-any.whl
Algorithm Hash digest
SHA256 a9e3aa7bf3314fc283f082b5784ccce3448999de551aae19967173c2732f456a
MD5 4b781d951f7dec1398bec5a99f187d5b
BLAKE2b-256 b5aaa09fdabe812a7ad65222a84af78231274d9a11a64c8075148a6e56cd299a

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