SnappySnag

io.github.snappysnag由 GitHub 帳號 snappysnag 發布v1.0.0更新於 Oct 29, 2026

Flutter in-app bug tracking, visual pin annotations, and device logs directly into your AI IDE.

發布方自己的服務:Snag

已驗證Streamable HTTP可網頁執行效率與工作流開發者工具

概覽

AI 產生的概覽

SnappySnag 的託管 MCP 伺服器讓 AI 程式助理讀取 Flutter 應用程式內的錯誤回報(標註點、截圖、元件樹、裝置日誌),並可將其標記為已解決。

可以做什麼
  • 取得最新的錯誤回報或使用者回饋,含標註點、截圖、中繼資料與裝置資訊
  • 依狀態、嚴重程度、來源或關鍵字搜尋並列出回饋工單
  • 取得單一工單的完整詳情,包括截圖、作用中的標註點與討論備註
  • 更新工單狀態(已解決、已忽略、待處理)並附上開發者解決說明
適用情境
適合透過 SnappySnag 收集 Flutter 視覺錯誤回報的團隊:讓程式助理查看被回報的畫面與元件脈絡、進行修正,並在不離開編輯器的情況下關閉工單。
執行需求
需要連線至 snappysnag.com 的遠端端點(透過 Streamable HTTP 與 OAuth 登入),或在本機以 Node.js 執行此伺服器。需要 SnappySnag 帳號及依專案限定的 MCP 金鑰,以 Bearer Authorization 標頭或金鑰參數傳入;未提供金鑰時,本機方式會以模擬工單的示範模式執行。
安裝前請注意
MCP 金鑰屬於憑證,請勿寫入共用設定,外洩後應立即撤銷或重新產生。伺服器可變更工單狀態並張貼解決備註,助理的操作會寫入你的 SnappySnag 專案。錯誤回報、截圖與裝置日誌會與 SnappySnag 託管服務之間傳輸。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 SnappySnag,將其新增到工作區。
  2. 連接 所需的 憑證。它們會被私密儲存,絕不會在公開頁面上展示。
  3. 為需要使用其工具的對話啟用該服務。

Web executable,透過 Streamable HTTP。 遠端服務在工作區中設定後即可從網頁執行環境執行。

交給代理程式安裝

把這段提示詞貼上到 Claude Code、Codex、Cursor 等代理程式,或 SourceWeft 對話中。代理程式會讀取該伺服器的安裝指南,先向你展示發布者、端點和登入方式,經你同意後再把它新增到你的客戶端。金鑰不會寫進任何命令。

閱讀 https://sourceweft.com/mcp/io.github.snappysnag%2Fsnappysnag/install.md,並按其中說明把這個 MCP 伺服器接入我的客戶端。修改任何設定之前,先告訴我它的發布者、端點和登入方式,等我確認。不要把 API 金鑰寫進命令或我會提交的檔案;問我金鑰應從哪裡取得。

檢視代理程式所依據的安裝指南

其他 MCP 客戶端

把它新增到你客戶端的 mcpServers 設定中。 客戶端會在首次連接時完成 OAuth 登入。

{
  "mcpServers": {
    "snappysnag": {
      "type": "http",
      "url": "https://snappysnag.com/api/mcp"
    }
  }
}

README

SnappySnag Model Context Protocol (MCP) Server

[MIT License] [SnappySnag] [pub.dev]

The official Model Context Protocol (MCP) integration for SnappySnag — seamlessly bridge Flutter in-app bug reports, pin annotations, screen diagnostics, and device logs directly into Cursor, Windsurf, Claude Desktop, and other AI coding assistants.


⚡ What is SnappySnag MCP?

When testing Flutter applications, QA testers and end-users pinpoint visual bugs or unexpected behaviors directly on the mobile screen. SnappySnag captures:

  • Exact visual pin coordinates and feedback comments
  • Annotated high-resolution screenshot
  • Active screen class & widget tree hierarchy
  • Real-time device logs (OS, platform, version, device metadata)
  • AI-generated root-cause insights and resolution prompts

With the SnappySnag MCP Server, your AI coding agent (in Cursor, Windsurf, Claude, etc.) can inspect these bug reports directly, jump straight to the relevant Flutter widget code, implement fixes, and mark tickets as resolved without ever switching context away from your editor.


🛠️ Available MCP Tools

ToolDescriptionKey Parameters
get_latest_feedbackFetches the most recent bug report or user feedback with full details (active pins, screenshot, metadata, device info).status (open | all), include_screenshot (true | false)
list_feedbacksSearches and lists feedback tickets matching filter criteria (status, severity, keyword). Returns lightweight summaries.status (open | resolved | ignored | all), severity, source, keyword, limit
get_feedback_detailRetrieves complete details for a specific feedback ID, including screenshot image, active pins, and discussion notes.feedback_id (required), include_screenshot
update_feedback_statusUpdates ticket status (resolved / ignored / open) and optionally attaches a developer resolution note.feedback_id (required), status (required), comment

🚀 Quick Start / Configuration

SnappySnag supports two connection options:

  1. Option A (Command / stdio with Demo Mode): Runs locally via standard MCP stdio. If no key is provided, an interactive Demo Mode with mock Flutter bug tickets is activated!
  2. Option B (Remote SSE / Streamable HTTP): Connects directly to SnappySnag's hosted endpoint without any local dependencies.

1. Get your MCP Secret Key (Optional for Demo)

  1. Sign in to your SnappySnag Dashboard.
  2. Open Project Settings (gear icon) -> Integrations or MCP tab.
  3. Click Generate MCP Secret Key and copy your key (snag_mcp_...).

2. Configure Your AI Editor

🔹 Option A: Command / stdio (npx or local build)
Cursor (.cursor/mcp.json)
json
{  "mcpServers": {    "snappysnag": {      "command": "node",      "args": ["path/to/snappy-snag-mcp/dist/index.js", "--key=YOUR_MCP_SECRET_KEY"]    }  }}

(Tip: Omit --key or set --key=demo to test with demo data!)

Claude Desktop (claude_desktop_config.json)
json
{  "mcpServers": {    "snappysnag": {      "command": "node",      "args": ["path/to/snappy-snag-mcp/dist/index.js", "--key=YOUR_MCP_SECRET_KEY"]    }  }}

🔹 Option B: Streamable HTTP (Remote SSE)
Cursor (.cursor/mcp.json)
json
{  "mcpServers": {    "snappysnag": {      "url": "https://snappysnag.com/api/mcp",      "headers": {        "Authorization": "Bearer YOUR_MCP_SECRET_KEY"      }    }  }}
Windsurf (~/.codeium/windsurf/mcp_config.json)
json
{  "mcpServers": {    "snappysnag": {      "serverUrl": "https://snappysnag.com/api/mcp",      "headers": {        "Authorization": "Bearer YOUR_MCP_SECRET_KEY"      }    }  }}

💡 Example Prompt Workflow

Once connected, you can instruct your AI assistant naturally:

"Check the latest open bug report from SnappySnag and fix the issue."

The AI agent will:

  1. Call get_latest_feedback(status: "open") to inspect the reported screen, pin position, and device specs.
  2. Read the referenced Flutter widget file in your repository.
  3. Apply the necessary code fix or layout adjustment.
  4. Call update_feedback_status(feedback_id: "...", status: "resolved", comment: "Fixed overflow in ProductCard layout").

🔒 Security & Privacy

  • Per-Project Scoped Keys: Each MCP Secret Key is strictly scoped to its designated project.
  • Instant Revocation: If compromised, keys can be regenerated or revoked with a single click in the dashboard.
  • Encrypted Transmission: All data and screenshot assets are delivered via HTTPS with short-lived signed URLs.

📚 Resources & Links


📄 License

This repository is licensed under the MIT License.

來源:README.md,提交 0a53e79

工具

0
該伺服器需要 API 金鑰等憑證,因此 SourceWeft 無法在沒有憑證的情況下讀取其工具,也未收錄。

版本歷史

1
  1. v1.0.0最新Oct 29, 2026

評分

已滿足適用檢查項的 85%

該評分衡量此收錄條目的完整程度,依據註冊中心條目、端點與公開來源計算得出。它不是對伺服器本身的評價,也不表示伺服器安全或目前可用:可連通性是帶日期的檢查結果,評分也不包含安裝量或使用者評價。

  • 近 30 天內可連通必需25 分
  • 已宣告認證方式必需10 分
  • 已列出工具15 分

    請讓伺服器在無憑證時回應 tools/list,或發布可在沙箱中無憑證啟動的軟體包。

  • 描述必需15 分
  • 圖示10 分
  • 文件15 分
  • 授權條款10 分

其他 Snag 整合