Skip to main content

MCP server for image reader using OpenAI vision API (gpt-4o-mini)

Project description

English | 한국어


English

gucken-image-reader is an MCP (Model Context Protocol) server that uses OpenAI's Vision API to generate descriptive text for images. It provides a single describe_image tool via stdio, enabling any MCP-compatible client (such as Claude or custom applications) to send an image file path and receive a detailed textual description in response.

Installation

Prerequisite: UV

If you don't have UV installed, follow these steps:

  • macOS / Linux

    curl -LsSf https://astral.sh/uv/install.sh | sh
    
  • Windows (PowerShell)

    powershell -ExecutionPolicy ByPass -Command "irm https://astral.sh/uv/install.ps1 | iex"
    

Configuration

In your working directory, create a .env file or export the environment variable directly:

OPENAI_API_KEY=your_openai_api_key_here

Integration with an MCP host

Add the following entry to your claude_desktop_config.json (or other MCP-compatible host configuration):

{
  "mcpServers": {
    "image-reader": {
      "command": "uvx",
      "args": ["gucken-image-reader"],
      "env": {
        "OPENAI_API_KEY": "your_openai_api_key_here"
      }
    }
  }
}
  • command: uvx
  • args: gucken-image-reader
  • env: Ensure that OPENAI_API_KEY is set.

Usage

  1. Complete the installation and configuration steps above.

  2. Start or restart your MCP host (e.g., the Claude desktop app); it will launch the gucken-image-reader server over stdio.

  3. Send an MCP request (JSON-RPC) calling the describe_image method with a local image file

  4. Receive a JSON response containing the image description generated by the model.

License

MIT


한국어

gucken-image-reader은 OpenAI Vision API를 활용해 이미지에 대한 설명을 생성하는 MCP(Model Context Protocol) 서버입니다. describe_image 툴을 stdio 방식으로 사용해 이미지를 텍스트로 설명해줍니다

설치

UV 설치 (아직 설치하지 않으셨다면)

  • macOS / Linux

    curl -LsSf https://astral.sh/uv/install.sh | sh
    
  • Windows (PowerShell)

    powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"
    

설정

다음 내용을 담은 .env 파일을 작업 디렉터리에 생성하거나, 환경 변수를 직접 설정하세요:

OPENAI_API_KEY=your_openai_api_key_here

MCP 호스트 통합

claude_desktop_config.json(또는 다른 MCP 호환 호스트 설정)에 다음 항목을 추가하세요:

{
  "mcpServers": {
    "image-reader": {
      "command": "uvx",
      "args": [
        "gucken-image-reader"
      ],
      "env": {
        "OPENAI_API_KEY": "your_openai_api_key_here"
      }
    }
  }
}
  • command: uvx
  • args: 콘솔 스크립트 이름 gucken-image-reader
  • env: OPENAI_API_KEY 설정 필수

사용 방법

  1. 위 설치·설정 과정을 완료합니다.
  2. MCP 호스트(예: Claude 앱)를 실행하거나 재시작하면 서버가 stdio로 구동됩니다.
  3. describe_image 툴을 호출하며 로컬 이미지 파일 경로를 전송합니다:
  4. 모델이 생성한 이미지 묘사 텍스트를 응답으로 받습니다.

라이선스

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

gucken_image_reader-1.1.3.tar.gz (4.8 kB view details)

Uploaded Source

Built Distribution

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

gucken_image_reader-1.1.3-py3-none-any.whl (5.4 kB view details)

Uploaded Python 3

File details

Details for the file gucken_image_reader-1.1.3.tar.gz.

File metadata

  • Download URL: gucken_image_reader-1.1.3.tar.gz
  • Upload date:
  • Size: 4.8 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.12.1

File hashes

Hashes for gucken_image_reader-1.1.3.tar.gz
Algorithm Hash digest
SHA256 01291fca6d5c6a32b726453b6c3304cd4ab2217127bf5252d3f9b03d1a59f3f0
MD5 00957e2fc6dd130525c05d31370a7c08
BLAKE2b-256 bb7759b9b119caf3bbfcb0af72c83dfcb1b60416ce8525a21b0ccba177504e77

See more details on using hashes here.

File details

Details for the file gucken_image_reader-1.1.3-py3-none-any.whl.

File metadata

File hashes

Hashes for gucken_image_reader-1.1.3-py3-none-any.whl
Algorithm Hash digest
SHA256 7849fa804fcc35161df3196e88b3550b9a6ad3177f2182c095340afbaeb7570d
MD5 7c46cd4f44db667e35c41f0c745dbf09
BLAKE2b-256 63639599cb88ba28f499c9c5c634e6df08c1f9745f43833e0ebc42a5da8aac82

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