MCP Feedback Collector

MCP Feedback Collector

Enables AI assistants to collect interactive user feedback through a modern GUI that supports text input, multiple image uploads (via file selection or clipboard paste), allowing users to provide comprehensive feedback with screenshots and comments.

Category
Visit Server

README

๐ŸŽฏ MCPๅ้ฆˆๆ”ถ้›†ๅ™จ

ไธ€ไธช็ŽฐไปฃๅŒ–็š„ Model Context Protocol (MCP) ๆœๅŠกๅ™จ๏ผŒไธบAIๅŠฉๆ‰‹ๆไพ›ไบคไบ’ๅผ็”จๆˆทๅ้ฆˆๆ”ถ้›†ๅŠŸ่ƒฝใ€‚

Version Python License

ๅœจcursor่ง„ๅˆ™ไธญๅฏไปฅไธ‹้ข่ฟ™ๆ ท้…็ฝฎ

"Whenever you want to ask a question, always call the MCP .

Whenever you're about to complete a user request, call the MCP instead of simply ending the process. Keep calling MCP until the user's feedback is empty, then end the request. mcp-feedback-collector.collect_feedback "

็›ธๅ…ณๆ•™็จ‹้“พๆŽฅ

ๆฒน็ฎก๏ผšhttps://youtu.be/aYtGm1xHNXI B็ซ™๏ผšhttps://www.bilibili.com/video/BV1J6jyzQE8P/

โœจ ไธป่ฆ็‰นๆ€ง

  • ๐ŸŽจ ็ŽฐไปฃๅŒ–็•Œ้ข - ็พŽ่ง‚็š„700x800ๅƒ็ด GUI๏ผŒๆ”ฏๆŒไธญๆ–‡็•Œ้ข๏ผŒ็ช—ๅฃๅฑ…ไธญๆ˜พ็คบๅนถ่‡ชๅŠจ็ฝฎ้กถ
  • โŒจ๏ธ ๅขžๅผบ้”ฎ็›˜ไบคไบ’ - ๆ”ฏๆŒ Enter ๆไบคใ€Esc ๅ–ๆถˆใ€Ctrl+V ็›ดๆŽฅ็ฒ˜่ดดๅ›พ็‰‡
  • ๐Ÿ“ท ๅคšๅ›พ็‰‡ๆ”ฏๆŒ - ๅŒๆ—ถ้€‰ๆ‹ฉๅคšๅผ ๅ›พ็‰‡๏ผŒๆ”ฏๆŒๆ–‡ไปถ้€‰ๆ‹ฉๅ’Œๅ‰ช่ดดๆฟ็ฒ˜่ดด
  • ๐Ÿ’ฌ ็ตๆดปๅ้ฆˆ - ๆ”ฏๆŒ็บฏๆ–‡ๅญ—ใ€็บฏๅ›พ็‰‡ๆˆ–ๆ–‡ๅญ—+ๅ›พ็‰‡็ป„ๅˆๅ้ฆˆ
  • โšก ้›ถ้…็ฝฎๅฎ‰่ฃ… - ไฝฟ็”จuvxไธ€้”ฎๅฎ‰่ฃ…๏ผŒๆ— ้œ€ๅคๆ‚้…็ฝฎ
  • ๐Ÿ”ง ๆ™บ่ƒฝ่ถ…ๆ—ถ - ๅฏ้…็ฝฎ็š„ๅฏน่ฏๆก†่ถ…ๆ—ถๆ—ถ้—ด๏ผŒ้ฟๅ…ๆ“ไฝœไธญๆ–ญ

๐Ÿš€ ๅฟซ้€Ÿๅผ€ๅง‹

1. ๅฎ‰่ฃ…uvx

pip install uvx

2. ้…็ฝฎClaude Desktop

ๅœจ claude_desktop_config.json ไธญๆทปๅŠ ๏ผš

{
  "mcpServers": {
    "mcp-feedback-collector": {
      "command": "uvx",
      "args": ["mcp-feedback-collector"],
      "env": {
        "PYTHONIOENCODING": "utf-8",
        "MCP_DIALOG_TIMEOUT": "600"
      }
    }
  }
}

3. ้‡ๅฏClaude Desktop

้…็ฝฎๅฎŒๆˆๅŽ้‡ๅฏClaude Desktopๅณๅฏไฝฟ็”จใ€‚

๐Ÿ› ๏ธ ๆ ธๅฟƒๅŠŸ่ƒฝ

collect_feedback()

ๆ”ถ้›†็”จๆˆทๅ้ฆˆ็š„ไธป่ฆๅทฅๅ…ท๏ผŒAIๅฏไปฅๆฑ‡ๆŠฅๅทฅไฝœๅ†…ๅฎน๏ผŒ็”จๆˆทๆไพ›ๆ–‡ๅญ—ๅ’Œๅ›พ็‰‡ๅ้ฆˆใ€‚

# AI่ฐƒ็”จ็คบไพ‹
result = collect_feedback("ๆˆ‘ๅทฒ็ปๅฎŒๆˆไบ†ไปฃ็ ไผ˜ๅŒ–ๅทฅไฝœ...")

pick_image()

ๅฟซ้€Ÿๅ›พ็‰‡้€‰ๆ‹ฉๅทฅๅ…ท๏ผŒ็”จไบŽๅ•ๅผ ๅ›พ็‰‡้€‰ๆ‹ฉๅœบๆ™ฏใ€‚

get_image_info()

่Žทๅ–ๅ›พ็‰‡ๆ–‡ไปถ็š„่ฏฆ็ป†ไฟกๆฏ๏ผˆๆ ผๅผใ€ๅฐบๅฏธใ€ๅคงๅฐ็ญ‰๏ผ‰ใ€‚

๐Ÿ–ผ๏ธ ็•Œ้ข้ข„่งˆ

๐ŸŽฏ ๅทฅไฝœๅฎŒๆˆๆฑ‡ๆŠฅไธŽๅ้ฆˆๆ”ถ้›†
โ”Œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”
โ”‚ ๐Ÿ“‹ AIๅทฅไฝœๅฎŒๆˆๆฑ‡ๆŠฅ                        โ”‚
โ”‚ โ”Œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ” โ”‚
โ”‚ โ”‚ [AIๆฑ‡ๆŠฅ็š„ๅทฅไฝœๅ†…ๅฎนๆ˜พ็คบๅœจ่ฟ™้‡Œ]         โ”‚ โ”‚
โ”‚ โ””โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”˜ โ”‚
โ””โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”˜

โ”Œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”
โ”‚ ๐Ÿ’ฌ ๆ‚จ็š„ๆ–‡ๅญ—ๅ้ฆˆ๏ผˆๅฏ้€‰๏ผ‰                  โ”‚
โ”‚ โ”Œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ” โ”‚
โ”‚ โ”‚ [ๅคš่กŒๆ–‡ๆœฌ่พ“ๅ…ฅๅŒบๅŸŸ]                   โ”‚ โ”‚
โ”‚ โ””โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”˜ โ”‚
โ””โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”˜

โ”Œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”
โ”‚ ๐Ÿ–ผ๏ธ ๅ›พ็‰‡ๅ้ฆˆ๏ผˆๅฏ้€‰๏ผŒๆ”ฏๆŒๅคšๅผ ๏ผ‰            โ”‚
โ”‚ [๐Ÿ“้€‰ๆ‹ฉๆ–‡ไปถ] [๐Ÿ“‹็ฒ˜่ดด] [โŒๆธ…้™ค]           โ”‚
โ”‚ [ๅ›พ็‰‡็ผฉ็•ฅๅ›พ้ข„่งˆๅŒบๅŸŸ]                     โ”‚
โ””โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”˜

[โœ… ๆไบคๅ้ฆˆ]  [โŒ ๅ–ๆถˆ]

โš™๏ธ ้…็ฝฎ่ฏดๆ˜Ž

่ถ…ๆ—ถ่ฎพ็ฝฎ

  • MCP_DIALOG_TIMEOUT: ๅฏน่ฏๆก†็ญ‰ๅพ…ๆ—ถ้—ด๏ผˆ็ง’๏ผ‰
    • ้ป˜่ฎค๏ผš300็ง’๏ผˆ5ๅˆ†้’Ÿ๏ผ‰
    • ๅปบ่ฎฎ๏ผš600็ง’๏ผˆ10ๅˆ†้’Ÿ๏ผ‰
    • ๅคๆ‚ๆ“ไฝœ๏ผš1200็ง’๏ผˆ20ๅˆ†้’Ÿ๏ผ‰

ๆ”ฏๆŒ็š„ๅ›พ็‰‡ๆ ผๅผ

PNGใ€JPGใ€JPEGใ€GIFใ€BMPใ€WebP

๐Ÿ’ก ไฝฟ็”จๅœบๆ™ฏ

  • โœ… AIๅฎŒๆˆไปปๅŠกๅŽๆ”ถ้›†็”จๆˆท่ฏ„ไปท
  • โœ… ๆ”ถ้›†ๅŒ…ๅซๆˆชๅ›พ็š„่ฏฆ็ป†ๅ้ฆˆ
  • โœ… ่Žทๅ–็”จๆˆทๅฏนไปฃ็ /่ฎพ่ฎก็š„ๆ„่ง
  • โœ… ๆ”ถ้›†bugๆŠฅๅ‘Šๅ’Œๆ”น่ฟ›ๅปบ่ฎฎ

๐Ÿ”ง ๆŠ€ๆœฏๆ ˆ

  • MCPๆก†ๆžถ: FastMCP
  • GUI: tkinter + PIL
  • ๅคš็บฟ็จ‹: threading + queue
  • ๅ›พ็‰‡ๅค„็†: Pillow

๐Ÿ“ ๆ›ดๆ–ฐๆ—ฅๅฟ—

v2.0.0 (2025-05-28)

  • ๐ŸŽจ ๅ…จๆ–ฐ็ŽฐไปฃๅŒ–UI่ฎพ่ฎก
  • ๐Ÿ“ท ๅคšๅ›พ็‰‡ๅŒๆ—ถๆไบคๆ”ฏๆŒ
  • ๐Ÿ–ผ๏ธ ๆจชๅ‘ๆปšๅŠจๅ›พ็‰‡้ข„่งˆ
  • ๐Ÿ’ซ ๅฝฉ่‰ฒๆŒ‰้’ฎๅ’Œๅ›พๆ ‡
  • ๐Ÿ”ง ไผ˜ๅŒ–็”จๆˆทไฝ“้ชŒ

๐Ÿ“„ ่ฎธๅฏ่ฏ

MIT License - ่ฏฆ่ง LICENSE ๆ–‡ไปถ

๐Ÿค ่ดก็Œฎ

ๆฌข่ฟŽๆไบคIssueๅ’ŒPull Request๏ผ


่ฎฉAIไธŽ็”จๆˆท็š„ไบคไบ’ๆ›ด้ซ˜ๆ•ˆ็›ด่ง‚๏ผ ๐ŸŽฏ

ๆ„Ÿ่ฐขๆ”ฏๆŒ

https://api.ssopen.top/ APIไธญ่ฝฌ็ซ™๏ผŒ290+AI ๅคงๆจกๅž‹๏ผŒๅฎ˜ๆ–นๆˆๆœฌไธƒๅˆ†ไน‹ไธ€๏ผŒๆ”ฏๆŒ้ซ˜ๅนถๅ‘๏ผ

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured