Jadx Mcp Plugin

Created By
mobilehackinglaba year ago
Overview

What is Jadx MCP Plugin?

The Jadx MCP Plugin is a Java-based plugin for the Jadx decompiler that exposes the Jadx API over HTTP, allowing live interaction with MCP clients like Claude through the Model Context Protocol (MCP). This facilitates intelligent navigation and automation of reverse engineering workflows, particularly for Android app security analysis.

How to use Jadx MCP Plugin?

To use the Jadx MCP Plugin, clone the repository, set up a Python virtual environment, install the required dependencies, and configure the MCP client (Claude) to connect to the plugin. After setup, load an APK or DEX file in Jadx to start using the plugin features.

Key features of Jadx MCP Plugin?

  • Exposes Jadx API over HTTP for live interaction.
  • Supports intelligent navigation and automation of reverse engineering tasks.
  • Provides tools for listing classes, fetching source code, inspecting methods/fields, and extracting code live.

Use cases of Jadx MCP Plugin?

  1. Reverse engineering Android applications for security analysis.
  2. Automating the extraction of decompiled code from APKs.
  3. Assisting developers in understanding and modifying existing Android applications.

FAQ from Jadx MCP Plugin?

  • What is the purpose of the Jadx MCP Plugin?

It allows for live interaction with the Jadx decompiler through MCP clients, enhancing reverse engineering workflows.

  • Is there a specific setup required for using the plugin?

Yes, you need to clone the repository, set up a Python virtual environment, and configure the MCP client accordingly.

  • Can I contribute to the Jadx MCP Plugin?

Yes, contributions such as PRs, feature requests, and tool extensions are welcome.

Project Info
Created At
a year ago
Updated At
a year ago
Author Name
mobilehackinglab
Star
-
Language
-
License
-

Recommend Servers

View All
Bring your real authenticated browser session to AI coding agents. Local-first MCP server + Chrome MV3 extension. No cloud. No telemetry.
@Cubenest

peek records the user's actual logged-in browser (DOM via rrweb, console events, network metadata, optional response bodies via opt-in Deep capture) through a Chrome MV3 extension. The extension ships events through a native-messaging stdio bridge to a local MCP server (peek-mcp), which persists them to a SQLite database at ~/.peek/sessions.db. AI coding agents (Claude Code, Cursor, Cline, Windsurf) read sessions from the database via 10 MCP tools: Tool What it does list_recent_sessions List recently recorded sessions (id, origin, ts, event count). get_session_summary LLM-readable narrative summary of a session. get_session_console_errors Console errors recorded in a session. get_session_network_errors Failed/notable network requests in a session. get_user_action_before_error Last N user actions before a console error. generate_playwright_repro Generate a runnable Playwright test from a session. get_dom_snapshot Reconstruct the DOM at a given timestamp. query_dom_history Timeline of attribute/text changes for a selector. request_authorization Side-panel consent for write actions (Level 3). execute_action Dispatch a UI action (gated by permission level + destructive blocklist). Why local-first matters Every other "browser session for AI" tool ships to a vendor cloud. peek's SQLite + extension live on the user's machine — no remote endpoints, no telemetry. The privacy policy (docs/peek/PRIVACY_POLICY.md) is the source of truth. Install # 1. Add the MCP server to Claude Code claude mcp add peek -- npx -y @peekdev/mcp # 2. Install the Chrome extension from the Chrome Web Store # (link added once the CWS listing is approved)

9 hours ago