android-tools-mcp: Instructions file for Claude Code

CLAUDE.md

android-tools-mcp CLAUDE.md is an instructions file for Claude Code from amsavarthan/android-tools-mcp. It costs 1,748 tokens per session, scanned A, original, Apache-2.0.

Project instructions for an IntelliJ plugin that exposes Android Studio's built-in tools to external coding agents through MCP, a standard way for software tools to communicate. It also describes the build, manual checks, and connection setup.

In plain words
What is it for?
Use it when building the plugin, creating its distribution ZIP, checking its server, or connecting Android Studio tools to Claude Code.
Why use it?
It explains how the plugin, its Python bridge, and the server fit together, reducing setup errors when connecting Android Studio to a coding agent.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions Claude Code.

This is amsavarthan/android-tools-mcp's own configuration. It tells Claude Code how to work on android-tools-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything android-tools-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to amsavarthan/android-tools-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/amsavarthan/android-tools-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/amsavarthan/android-tools-mcp

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for android-tools-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/amsavarthan/android-tools-mcp/claude-md.svg)](https://agentmods.dev/instructions/amsavarthan/android-tools-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/amsavarthan/android-tools-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/amsavarthan/android-tools-mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,748 This file is loaded in full into every session.
When invoked 1,748 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.01748 $0.01748
Opus 5 $0.00874 $0.00874
Sonnet 5 $0.00350 $0.00350
Haiku 4.5 $0.00175 $0.00175

Measured 7d ago against content hash 2355bac109d8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

android-tools-mcp CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 147 lines

How it starts

The opening of the file, as written. The whole thing — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.

android-tools-mcp

IntelliJ plugin that bridges Android Studio's built-in Gemini agent tools to external AI coding tools via the Model Context Protocol (MCP).

Build

Requires a local Android Studio installation. The build resolves its path from (in order): local.properties, env var ANDROID_STUDIO_PATH, or /Applications/Android Studio.app.

./gradlew buildPlugin

Output ZIP lands in build/distributions/. Install it via Settings > Plugins > Install from Disk.

Run / Test

There are no automated tests. To verify manually:

  1. Install the plugin ZIP in Android Studio and open a project
  2. Run python3 scripts/health-check.py (or python3 scripts/health-check.py <port>) to confirm the SSE server is up
  3. Connect via Claude Code (see below) and invoke a tool

Connect with Claude Code

claude mcp add android-studio -- python3 scripts/android-studio-mcp.py

The Python wrapper script converts stdio ↔ SSE so CLI-based MCP clients can connect. Works on macOS, Linux, and Windows (Python 3.7+, stdlib only).

Architecture

Startup flow

  1. McpBridgeStartupActivity fires on project open
  2. Calls McpBridgeService.start() which discovers tools and starts the SSE server
  3. A second discovery pass runs after 30 s to catch late-loading tools

Tool discovery

McpBridgeService queries both of the Gemini plugin's parallel agent-tool extension points and merges the results, preferring V2 where a tool name appears on both:

V1 V2
Extension point com.google.aiplugin.agentToolsProvider com.google.studiobot.agentsdk.toolsProvider
Package com.google.aiplugin.agents com.google.studiobot.agentsdk
Enumeration getToolSets(Project) getInstance(Project, ToolSetId) per enum value — there is no bulk accessor
Invocation createToolHandler(ToolContext, Content.FunctionCall) then handle() returns a Response createToolHandler(ToolContext, Map) then run(MutableToolCallStep, Trajectory) writes the Response into the step
Status Legacy — every implementation is …V1-suffixed Current, and the only place newer tools land

Read the full file on GitHub · 147 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 7d ago First seen · 147 lines · 1,748 tokens per session scan A 2355bac109d8

Subscribe to this mod's changes

android-tools-mcp CLAUDE.md is an instructions file published in the GitHub repository amsavarthan/android-tools-mcp (27 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 1,748 tokens to every session, about $0.0087 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other instructions, from other repositories

awesome-ai-setup riverpod.instructions.md

Instructions for shuchitajain/awesome-ai-setup, covering riverpod conventions, provider types, naming, state classes and async state pattern.

shuchitajain/awesome-ai-setup · 1,742 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens