de en es ja ko ru zh

Clipboard to Supabase MCP Helper

Name: Clipboard to Supabase MCP Helper
Author: martinbowling

by martinbowling

Overview Schema Source Related Servers Discussions Admin

TypeScript

Local

Supabase MCP 도우미로 클립보드 전송

시스템 클립보드를 모니터링하고 복사된 이미지를 Supabase 저장소에 업로드한 다음 공개(또는 서명된) URL을 클립보드에 다시 쓰는 로컬 에이전트입니다.

특징

클릭 없이 이미지 호스팅: 이미지를 복사하고 즉시 URL을 받으세요
낮은 지연 시간: 복사에서 URL까지 800ms 미만
크로스 플랫폼: macOS, Windows 및 Linux에서 작동합니다.
MCP 통합: 클립보드 이미지 업로드를 MCP 엔드포인트로 노출
자동 시작: 시스템 시작 시 실행되도록 구성
효율적인 감지: CPU 사용량이 낮은 해시 기반 중복 제거

Related MCP server: ClipMCP

필수 조건

노드.js 18+
저장소가 활성화된 Supabase 계정
플랫폼별 종속성:
- macOS: pngpaste ( brew install pngpaste )
- Windows/Linux: 기본 OS 클립보드 액세스

설치

저장소를 복제합니다.

지엑스피1

종속성 설치:

npm install

.env.example 기반으로 .env 파일을 만듭니다.

SUPABASE_URL=https://<project>.supabase.co
SUPABASE_SERVICE_ROLE_KEY=your-service-role-key
BUCKET=media
MCP_PORT=3333

Supabase 연결을 테스트하세요.

npm run test:supabase

프로젝트를 빌드하세요:

npm run build

시스템 서비스로 설치:

macOS의 경우:

npm run install:macos

Linux의 경우:

npm run install:linux

Windows의 경우:

npm run install:windows

용법

도우미를 설치하고 실행하면 다음 작업이 수행됩니다.

클립보드에서 이미지 변경 사항을 모니터링합니다(300ms마다 폴링).
복사된 이미지를 Supabase 버킷에 업로드하세요.
공개 URL을 클립보드에 다시 넣어 붙여넣기 준비를 하세요.

서비스 실행

클립보드 도우미는 두 가지 모드로 실행할 수 있습니다.

표준 모드(기본값)

npm start

이는 명령줄 사용에 적합한 StdioServerTransport를 사용하여 MCP 서버를 실행합니다.

HTTP 모드

npm run start:http

이는 적절한 REST API 엔드포인트를 사용하여 포트 3333(구성 가능)에서 Express HTTP 서버를 실행합니다.

MCP 통합

도우미는 다음 MCP 엔드포인트를 노출합니다.

클립보드 이미지 업로드

HTTP 서버 모드의 경우:

POST http://localhost:3333/mcp

요청 본문:

{
  "id": "1",
  "jsonrpc": "2.0",
  "method": "tool",
  "params": {
    "name": "upload_clipboard_image",
    "input": {}
  }
}

응답:

{
  "id": "1",
  "jsonrpc": "2.0",
  "result": {
    "content": [
      {
        "type": "text",
        "text": "https://your-project.supabase.co/storage/v1/object/public/media/clips/xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx.png"
      }
    ]
  }
}

오래된 파일 정리

도우미는 오래된 파일을 수동으로 정리하기 위한 MCP 엔드포인트도 제공합니다.

요청 본문:

{
  "id": "1",
  "jsonrpc": "2.0",
  "method": "tool",
  "params": {
    "name": "cleanup_old_files",
    "input": {
      "days": 30
    }
  }
}

응답:

{
  "id": "1",
  "jsonrpc": "2.0",
  "result": {
    "content": [
      {
        "type": "text",
        "text": "Cleanup completed: Deleted 5 files older than 30 days. Failed: 0."
      }
    ]
  }
}

days 매개변수는 선택 사항입니다. 지정하지 않으면 RETENTION_DAYS 환경 변수의 값이 사용됩니다.

작동 원리

변경 감지 : 300ms마다 클립보드를 폴링하고 이미지 데이터의 SHA-1 해시를 계산합니다.
중복 제거 : 해시 비교를 기반으로 새 이미지나 변경된 이미지만 처리합니다.
플랫폼 적응 : 플랫폼별 방법을 사용하여 클립보드 이미지를 캡처합니다.
Supabase 통합 : 고유한 UUID를 사용하여 Supabase 버킷에 이미지를 업로드합니다.
MCP Endpoint : 모델 컨텍스트 프로토콜을 통해 AI 에이전트에 기능을 노출합니다.
자동 정리 : 구성된 보존 기간(기본값: 30일)보다 오래된 이미지를 주기적으로 제거합니다.

플랫폼별 참고 사항

맥OS

pngpaste 필요합니다: brew install pngpaste 로 설치하세요
자동 시작을 위해 LaunchAgents를 사용합니다.

윈도우

이미지 캡처를 위해 PowerShell의 System.Windows.Forms.Clipboard를 사용합니다.
자동 시작을 위해 Windows 레지스트리를 사용합니다.

리눅스

클립보드 액세스를 위해 xclip(X11) 또는 wl-paste(Wayland)를 사용합니다.
자동 시작을 위해 systemd를 사용합니다.

개발

# Run with live reload (stdio mode)
npm run dev

# Run with live reload (HTTP mode)
npm run dev:http

# Build for production
npm run build

# Run stdio version
npm start

# Run HTTP version
npm run start:http

특허

MIT

Available Tools

2 tools

cleanup_old_filesD

ParametersJSON Schema

Name	Required	Description	Default
No parameters

TDQS

D1/5.0

Behavior1/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Tool has no description.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness1/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Tool has no description.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness1/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Tool has no description.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters1/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Tool has no description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose1/5

Does the description clearly state what the tool does and how it differs from similar tools?

Tool has no description.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines1/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Tool has no description.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

upload_clipboard_imageD

ParametersJSON Schema

Name	Required	Description	Default
No parameters

TDQS

D1/5.0

Behavior1/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Tool has no description.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness1/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Tool has no description.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness1/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Tool has no description.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters1/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Tool has no description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose1/5

Does the description clearly state what the tool does and how it differs from similar tools?

Tool has no description.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines1/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Tool has no description.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

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

2 tool updatesv1.0.0Jan 3, 2026
- Changedcleanup_old_files1 field changed
  - addedInput schema / properties
```
Added value: +{}
```
- Changedupload_clipboard_image1 field changed
  - removedInput schema / additionalProperties
```
Removed value: -false
```
2 tool updatesMay 11, 2025
- First observedcleanup_old_files
- First observedupload_clipboard_image

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

D1.8/5.0

Scored 2026-04-18 10:05 across 2 tools

Disambiguation5/5

The two tools have clearly distinct purposes: cleanup_old_files handles file management, while upload_clipboard_image handles image uploads. There is no overlap in functionality, making them easy to distinguish.

Naming Consistency5/5

Both tools follow a consistent verb_noun pattern with snake_case naming: cleanup_old_files and upload_clipboard_image. The naming is predictable and uniform across the set.

Tool Count2/5

With only 2 tools, the server feels thin for a 'Clipboard to Supabase MCP Helper' that might imply broader clipboard or Supabase integration. This minimal set likely leaves gaps in functionality.

Completeness2/5

Inferred domain includes clipboard operations and Supabase integration, but the tools only cover image uploads and file cleanup. Missing obvious functions like handling text/data from clipboard or other Supabase CRUD operations.

Maintenance

ActivityInactive

ResponsivenessNo issues

Resources

GitHub Repository

Need Help?

Related Servers

Related MCP Connectors

pixelvault AOAuth
io.github.pixelvault-dev
Agent-first image hosting — upload images and get instant CDN URLs.
Cloud Storage Multimedia Processing
2
NoClick AOAuth
io.github.noclickapp
Build agents to automate any background task. Works with your ChatGPT/Claude subscription.
App Automation Autonomous Agents
4712
Run402 A
com.run402
x402 pay-per-call infra for agents: $0.03 image generation, Postgres, auth, storage, functions.
Cloud Platforms Agent Orchestration Databases
4224
agent-cloud-tools A
com.83blue.upload
Free no-signup cloud tools for AI agents: file transfer, static site hosting, memory, handoff.
Agent Orchestration Cloud Platforms Knowledge & Memory
91

Related MCP Servers

clipboard-vision-mcp
AI & Machine Learning Image & Video Processing
Capetlevrai
A
license
B
quality
D
maintenance
Enables text-only AI models to understand clipboard images by describing them through a vision model, eliminating manual file saving.
Updated a month ago (2026-08-14 07:05 UTC)
12
44
MIT
ClipMCP
Developer Tools Knowledge & Memory Search
susmetaa01
A
license
Not graded
quality
D
maintenance
A standalone clipboard history MCP server for macOS that monitors clipboard in real-time, stores history locally in SQLite, and exposes it to any MCP-compatible AI assistant.
Updated 5 months ago (2026-04-19 14:40 UTC)
5
MIT
openai-gpt-image-1-mcp
Image & Video Processing AI & Machine Learning
DevRico003
A
license
Not graded
quality
D
maintenance
Provides AI agents and coding assistants with image generation and editing capabilities using OpenAI's GPT-image-1 model, with support for local or Supabase storage.
Updated a year ago (2025-05-15 16:20 UTC)
3
MIT
image-recognition-mcp
Image & Video Processing AI & Machine Learning
llt22
A
license
A
quality
B
maintenance
Gives vision-less LLMs the ability to recognize clipboard screenshots and images by proxying to an OpenAI-compatible vision model.
Updated 3 months ago (2026-07-01 07:01 UTC)
1
12 npm
2
MIT

Supabase MCP 도우미로 클립보드 전송

특징

필수 조건

설치

용법

서비스 실행

표준 모드(기본값)

HTTP 모드

MCP 통합

클립보드 이미지 업로드

오래된 파일 정리

작동 원리

플랫폼별 참고 사항

맥OS

윈도우

리눅스

개발

특허

Available Tools

TDQS

TDQS

Tool Schema Changelog

TDQS

Maintenance

Resources

Related MCP Connectors

Related MCP Servers

clipboard-vision-mcp

ClipMCP

openai-gpt-image-1-mcp

image-recognition-mcp