android-mcp-toolkit

android-mcp-toolkit

A growing collection of MCP tools for Android Development. Currently features a deterministic Figma-SVG-to-Android-XML converter, with plans for Gradle analysis, Resource management, and ADB integration tools.

Category
访问服务器

README

Android MCP Toolkit for AI Agents

Small MCP server with two tools:

  • Fast SVG → Android VectorDrawable conversion (cached, file or inline).
  • adb logcat reader with package/pid/tag filters for quick crash triage.

Why this exists

The Mission: Bringing Native Android to the AI Agent Era

While the AI ecosystem flourishes with web-first tools, Android development often feels left behind. This MCP server is my answer to that gap—a dedicated bridge connecting AI Agents directly to the Android toolchain.

⚡ Zero-Friction Asset Conversion: Convert SVGs to VectorDrawables instantly without the overhead of launching Android Studio.

🔍 Direct Diagnostic Access: Empower agents to pull, filter, and analyze adb logcat streams (by package, PID, or tag) in real-time.

🤖 Agent-Native Architecture: Deliver structured, scriptable outputs that LLMs can parse and act upon efficiently.

🚀 Built for Extensibility: A solid foundation designed to grow, paving the way for future utilities like bitmap helpers and asset validation.

Pairing ideas

  • Figma MCP: grab SVGs from designs, feed to convert-svg-to-android-drawable to get XML for Android resources.
  • Debugging: while running the app, call read-adb-logcat with package name or tag to capture crashes and filtered logs without leaving the MCP client.

Previews

SVG to VectorDrawable

  • Figma request → SVG extraction
    Figma request via MCP
  • Flag conversion preview (single)
    Flag conversion preview
  • Batch flag review (side-by-side)
    Batch flag review
  • Batch run via MCP (console)
    Batch run via MCP

ADB logcat tool

  • Crash capture prompt (inputs + filters)
    Crash logcat prompt
  • Response preview (summarized logcat)
    Response gap prompt

Current tools

  • convert-svg-to-android-drawable

    • Inputs: svg (inline) or svgPath (file path). Optional: outputPath, floatPrecision (default 2), fillBlack (default false), xmlTag (default false), tint, cache (default true).
    • Output: VectorDrawable XML text; also writes to disk when outputPath is provided.
    • Performance: LRU cache (32 entries) keyed by SVG + options plus fast reuse in-session.
    • Converter: vendored fork in vendor/svg2vectordrawable with fixes for rgb()/rgba(), hsl()/hsla(), and named colors. Upstream license: vendor/svg2vectordrawable/LICENSE (MIT).
  • read-adb-logcat

    • Inputs: packageName (resolve pid via adb shell pidof -s), pid (explicit), tag, priority (V|D|I|W|E|F|S, default V), maxLines (tail count, default 200, max 2000), timeoutMs (default 5000, max 15000).
    • Behavior: Runs adb logcat -d -t <maxLines> with optional --pid=<pid> and -s tag:priority.
    • Output: Returns the logcat text; if no lines are returned, responds with a short message.
    • Notes: Requires adb available in PATH and a connected device/emulator. Provide at least one of packageName, pid, or tag to scope logs.
  • get-pid-by-package

    • Inputs: packageName (required), timeoutMs (default 5000, max 15000).
    • Behavior: Resolves pid via adb shell pidof -s <package>.
    • Notes: Use this first, then pass pid to other logcat tools for noise-free filtering.
  • get-current-activity

    • Inputs: timeoutMs (default 5000, max 15000).
    • Behavior: Parses adb shell dumpsys window for mCurrentFocus / mFocusedApp to reveal the currently focused window (useful even in single-activity setups to confirm top window).
  • fetch-crash-stacktrace

    • Inputs: packageName (optional, resolves pid), maxLines (default 400, max 2000), timeoutMs (default 5000, max 15000).
    • Behavior: Pulls crash buffer via adb logcat -b crash -d -t <maxLines>; filters by --pid when package is provided.
  • check-anr-state

    • Inputs: maxLines (default 400, max 2000), timeoutMs (default 5000, max 15000).
    • Behavior: Fetches ActivityManager:E *:S (recent ANR logs) and best-effort reads /data/anr/traces.txt (stat + tail 200 lines). May require root/debuggable.
  • clear-logcat-buffer

    • Inputs: timeoutMs (default 5000, max 15000).
    • Behavior: Runs adb logcat -c to clear buffers before a new scenario.

Roadmap (planned)

  • Additional MCP tools for Android assets (e.g., batch conversions, validations, optimizers).
  • Optional resource prompts for common Android drawables/templates.
  • Upcoming MCP utilities (planned):
    • Logcat reader: stream and filter Android logcat output via MCP.
    • Asset checkers: flag common drawable issues (size, alpha, color profile).
    • Batch conversions: multi-SVG to VectorDrawable with consistent options.
    • Template prompts: quick-start drawable/XML snippets for common patterns.

Quick start

  • npm install
  • npm run build
  • node dist/index.js (stdio MCP server)

Run via npx

  • Global: npx android-mcp-toolkit

Use in Cursor (MCP config)

Add to your Cursor settings JSON:

{
  "mcpServers": {
    "figma-desktop": {
      "url": "http://127.0.0.1:3845/mcp"
    },
    "android-mcp-toolkit": {
      "command": "npx",
      "args": [
        "-y",
        "android-mcp-toolkit"
      ]
    }
  }
}

The npx call downloads the published package; no local path required.

Quick install via Cursor deep link:

  • cursor://anysphere.cursor-deeplink/mcp/install?name=android-mcp-toolkit&config=eyJjb21tYW5kIjoibnB4IC15IGFuZHJvaWQtbWNwLXRvb2xraXQifQ%3D%3D

Examples

  • Input SVG: sample_svg.svg
  • Output VectorDrawable: examples/sample_svg.xml

Notes

  • Transport: stdio via @modelcontextprotocol/sdk.
  • Base deps kept minimal; everything needed to convert SVGs is vendored/included.

Contact

  • nam.nv205106@gmail.com

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选