{"id":28769806,"url":"https://github.com/zinja-coder/jadx-ai-mcp","last_synced_at":"2026-02-28T19:00:46.494Z","repository":{"id":286790375,"uuid":"962125208","full_name":"zinja-coder/jadx-ai-mcp","owner":"zinja-coder","description":"Plugin for JADX to integrate MCP server","archived":false,"fork":false,"pushed_at":"2025-12-29T19:36:30.000Z","size":29018,"stargazers_count":981,"open_issues_count":6,"forks_count":112,"subscribers_count":7,"default_branch":"jadx-ai","last_synced_at":"2026-01-01T20:38:20.928Z","etag":null,"topics":["ai","java","llm","mcp","mcp-server","mcp-servers","mobile","model-context-protocol","model-context-protocol-servers","pentesting","reverse-engineering","sast","vapt"],"latest_commit_sha":null,"homepage":"","language":"Java","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":"skylot/jadx","license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/zinja-coder.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","funding":".github/FUNDING.yml","license":"LICENSE","code_of_conduct":"CODE_OF_CONDUCT.md","threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":"SECURITY.md","support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null},"funding":{"github":"zinja-coder","ko_fi":"zinjacoder"}},"created_at":"2025-04-07T17:28:54.000Z","updated_at":"2026-01-01T17:45:02.000Z","dependencies_parsed_at":"2025-06-25T00:11:08.455Z","dependency_job_id":"f691170d-f3fa-4f7c-8307-94088c1e8119","html_url":"https://github.com/zinja-coder/jadx-ai-mcp","commit_stats":null,"previous_names":["zinja-coder/jadx-ai","zinja-coder/jadx-ai-mcp"],"tags_count":27,"template":false,"template_full_name":null,"purl":"pkg:github/zinja-coder/jadx-ai-mcp","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zinja-coder%2Fjadx-ai-mcp","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zinja-coder%2Fjadx-ai-mcp/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zinja-coder%2Fjadx-ai-mcp/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zinja-coder%2Fjadx-ai-mcp/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/zinja-coder","download_url":"https://codeload.github.com/zinja-coder/jadx-ai-mcp/tar.gz/refs/heads/jadx-ai","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zinja-coder%2Fjadx-ai-mcp/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":29948228,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-02-28T18:42:55.706Z","status":"ssl_error","status_checked_at":"2026-02-28T18:42:48.811Z","response_time":90,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.6:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["ai","java","llm","mcp","mcp-server","mcp-servers","mobile","model-context-protocol","model-context-protocol-servers","pentesting","reverse-engineering","sast","vapt"],"created_at":"2025-06-17T13:04:14.548Z","updated_at":"2026-02-28T19:00:46.477Z","avatar_url":"https://github.com/zinja-coder.png","language":"Java","funding_links":["https://github.com/sponsors/zinja-coder","https://ko-fi.com/zinjacoder"],"categories":["Security","Security \u0026 Attestation MCP Servers","AI","📚 Projects (1974 total)","サーバー実装","Weapons","Content Creation","Containerised MCP Servers","📦 Other","逆向破解","MCP Servers","📱 Android / IOS 安全分析","MCP Servers \u0026 Protocol"],"sub_categories":["Reverse Engineering","MCP Servers","🔒 \u003ca name=\"security\"\u003e\u003c/a\u003eセキュリティ","Android","AI \u0026 Machine Learning","Security \u0026 Reverse Engineering"],"readme":"\u003cdiv align=\"center\"\u003e\n\n# JADX-AI-MCP (Part of Zin MCP Suite)\n\n⚡ Fully automated MCP server + JADX plugin built to communicate with LLM through MCP to analyze Android APKs using LLMs like Claude — uncover vulnerabilities, analyze APK, and reverse engineer effortlessly.\n\n![GitHub contributors JADX-AI-MCP](https://img.shields.io/github/contributors/zinja-coder/jadx-ai-mcp)\n![GitHub contributors JADX-MCP-SERVER](https://img.shields.io/github/contributors/zinja-coder/jadx-mcp-server)\n![GitHub all releases](https://img.shields.io/github/downloads/zinja-coder/jadx-ai-mcp/total)\n![GitHub release (latest by SemVer)](https://img.shields.io/github/downloads/zinja-coder/jadx-ai-mcp/latest/total)\n![Latest release](https://img.shields.io/github/release/zinja-coder/jadx-ai-mcp.svg)\n![Java 11+](https://img.shields.io/badge/Java-11%2B-blue)\n![Python 3.10+](https://img.shields.io/badge/python-3%2E10%2B-blue)\n[![License](http://img.shields.io/:license-apache-blue.svg)](http://www.apache.org/licenses/LICENSE-2.0.html)\n\n#### ⭐ Contributors\n\nThanks to these wonderful people for their contributions ⭐\n\u003ctable\u003e\n  \u003ctr align=\"center\"\u003e\n  \u003ctd\u003e\n      \u003ca href=\"https://github.com/ljt270864457\"\u003e\n        \u003cimg src=\"https://avatars.githubusercontent.com/u/8609890?v=4\" width=\"30px;\" alt=\"\"/\u003e\n        \u003cbr /\u003e\u003csub\u003e\u003cb\u003eljt270864457\u003c/b\u003e\u003c/sub\u003e\n      \u003c/a\u003e\n    \u003c/td\u003e\n    \u003ctd\u003e\n      \u003ca href=\"https://github.com/p0px\"\u003e\n        \u003cimg src=\"https://avatars.githubusercontent.com/u/161268024?v=4\" width=\"30px;\" alt=\"\"/\u003e\n        \u003cbr /\u003e\u003csub\u003e\u003cb\u003ep0px\u003c/b\u003e\u003c/sub\u003e\n      \u003c/a\u003e\n    \u003c/td\u003e\n    \u003ctd\u003e\n      \u003ca href=\"https://github.com/badmonkey7\"\u003e\n        \u003cimg src=\"https://avatars.githubusercontent.com/u/41368882?v=4\" width=\"30px;\" alt=\"\"/\u003e\n        \u003cbr /\u003e\u003csub\u003e\u003cb\u003ebadmonkey7\u003c/b\u003e\u003c/sub\u003e\n      \u003c/a\u003e\n    \u003c/td\u003e\n       \u003ctd\u003e\n      \u003ca href=\"https://github.com/tiann\"\u003e\n        \u003cimg src=\"https://avatars.githubusercontent.com/u/4233744?v=4\" width=\"30px;\" alt=\"\"/\u003e\n        \u003cbr /\u003e\u003csub\u003e\u003cb\u003etiann\u003c/b\u003e\u003c/sub\u003e\n      \u003c/a\u003e\n    \u003c/td\u003e\n    \u003ctd\u003e\n      \u003ca href=\"https://github.com/ZERO-A-ONE\"\u003e\n        \u003cimg src=\"https://avatars.githubusercontent.com/u/18625356?v=4\" width=\"30px;\" alt=\"\"/\u003e\n        \u003cbr /\u003e\u003csub\u003e\u003cb\u003eZERO-A-ONE\u003c/b\u003e\u003c/sub\u003e\n      \u003c/a\u003e\n    \u003c/td\u003e\n    \u003ctd\u003e\n      \u003ca href=\"https://github.com/neoz\"\u003e\n        \u003cimg src=\"https://avatars.githubusercontent.com/u/360582?v=4\" width=\"30px;\" alt=\"\"/\u003e\n        \u003cbr /\u003e\u003csub\u003e\u003cb\u003eneoz\u003c/b\u003e\u003c/sub\u003e\n      \u003c/a\u003e\n    \u003c/td\u003e\n    \u003ctd\u003e\n      \u003ca href=\"https://github.com/SamadiPour\"\u003e\n        \u003cimg src=\"https://avatars.githubusercontent.com/u/24422125?v=4\" width=\"30px;\" alt=\"\"/\u003e\n        \u003cbr /\u003e\u003csub\u003e\u003cb\u003eSamadiPour\u003c/b\u003e\u003c/sub\u003e\n      \u003c/a\u003e\n    \u003c/td\u003e\n    \u003ctd\u003e\n      \u003ca href=\"https://github.com/wuseluosi\"\u003e\n        \u003cimg src=\"https://avatars.githubusercontent.com/u/192840340?v=4\" width=\"30px;\" alt=\"\"/\u003e\n        \u003cbr /\u003e\u003csub\u003e\u003cb\u003ewuseluosi\u003c/b\u003e\u003c/sub\u003e\n      \u003c/a\u003e\n    \u003c/td\u003e\n    \u003ctd\u003e\n      \u003ca href=\"https://github.com/CainYzb\"\u003e\n        \u003cimg src=\"https://avatars.githubusercontent.com/u/50669073?v=4\" width=\"30px;\" alt=\"\"/\u003e\n        \u003cbr /\u003e\u003csub\u003e\u003cb\u003eCainYzb\u003c/b\u003e\u003c/sub\u003e\n      \u003c/a\u003e\n    \u003c/td\u003e\n    \u003ctd\u003e\n      \u003ca href=\"https://github.com/tbodt\"\u003e\n        \u003cimg src=\"https://avatars.githubusercontent.com/u/5678977?v=4\" width=\"30px;\" alt=\"\"/\u003e\n        \u003cbr /\u003e\u003csub\u003e\u003cb\u003etbodt\u003c/b\u003e\u003c/sub\u003e\n      \u003c/a\u003e\n    \u003c/td\u003e\n    \u003ctd\u003e\n      \u003ca href=\"https://github.com/LilNick0101\"\u003e\n        \u003cimg src=\"https://avatars.githubusercontent.com/u/100995805?v=4\" width=\"30px;\" alt=\"\"/\u003e\n        \u003cbr /\u003e\u003csub\u003e\u003cb\u003eLilNick0101\u003c/b\u003e\u003c/sub\u003e\n      \u003c/a\u003e\n    \u003c/td\u003e\n    \u003ctd\u003e\n      \u003ca href=\"https://github.com/lwsinclair\"\u003e\n        \u003cimg src=\"https://avatars.githubusercontent.com/u/2829939?v=4\" width=\"30px;\" alt=\"\"/\u003e\n        \u003cbr /\u003e\u003csub\u003e\u003cb\u003elwsinclair\u003c/b\u003e\u003c/sub\u003e\n      \u003c/a\u003e\n    \u003c/td\u003e\n  \u003c/tr\u003e\n\u003c/table\u003e\n\n\n\n\u003c/div\u003e\n\n\u003c!-- It is a still in early stage of development, so expects bugs, crashes and logical erros.--\u003e\n\n\u003c!-- Standalone Plugin for [JADX](https://github.com/skylot/jadx) (Started as Fork) with Model Context Protocol (MCP) integration for AI-powered static code analysis and real-time code review and reverse engineering tasks using Claude.--\u003e\n\n\n\u003cdiv align=\"center\"\u003e\n    \u003cimg alt=\"banner\" height=\"480px\" widht=\"620px\" src=\"docs/assets/img.png\"\u003e\n\u003c/div\u003e\n\n\u003c!-- ![jadx-ai-banner.png](docs/assets/img.png) Image generated using AI tools. --\u003e\n\n#### Read The Docs\n - Read The Docs is now live: https://jadx-ai-mcp.readthedocs.io/en/latest/\n\n---\n\n## 🤖 What is JADX-AI-MCP?\n\n**JADX-AI-MCP** is a plugin for the [JADX decompiler](https://github.com/skylot/jadx) that integrates directly with [Model Context Protocol (MCP)](https://github.com/anthropic/mcp) to provide **live reverse engineering support with LLMs like Claude**.\n\nThink: \"Decompile → Context-Aware Code Review → AI Recommendations\" — all in real time.\n\n#### High Level Sequence Diagram\n\n```mermaid\nsequenceDiagram\nLLM CLIENT-\u003e\u003eJADX MCP SERVER: INVOKE MCP TOOL\nJADX MCP SERVER-\u003e\u003eJADX AI MCP PLUGIN: INVOKE HTTP REQUEST\nJADX AI MCP PLUGIN-\u003e\u003eREQUEST HANDLERS: INVOKE HTTP REQUEST HANDLER\nREQUEST HANDLERS-\u003e\u003eJADX GUI: PERFORM ACTION/GATHER DATA\nJADX GUI-\u003e\u003eREQUEST HANDLERS: ACTION PERFORMED/DATA GATHERED\nREQUEST HANDLERS-\u003e\u003eJADX AI MCP PLUGIN: CRAFT HTTP RESPONSE\nJADX AI MCP PLUGIN-\u003e\u003eJADX MCP SERVER:HTTP RESPONSE\nJADX MCP SERVER-\u003e\u003eLLM CLIENT: MCP TOOL RESULT\n```\n\n### Watch the demos!\n\n- **Perform quick analysis**\n  \nhttps://github.com/user-attachments/assets/b65c3041-fde3-4803-8d99-45ca77dbe30a\n\n- **Quickly find vulnerabilities**\n\nhttps://github.com/user-attachments/assets/c184afae-3713-4bc0-a1d0-546c1f4eb57f\n\n- **Multiple AI Agents Support**\n\nhttps://github.com/user-attachments/assets/6342ea0f-fa8f-44e6-9b3a-4ceb8919a5b0\n\n- **Run with your favorite LLM Client**\n\nhttps://github.com/user-attachments/assets/b4a6b280-5aa9-4e76-ac72-a0abec73b809\n\n- **Analyze The APK Resources**\n\nhttps://github.com/user-attachments/assets/f42d8072-0e3e-4f03-93ea-121af4e66eb1\n\n- **Your AI Assistant during debugging of APK using JADX**\n\nhttps://github.com/user-attachments/assets/2b0bd9b1-95c1-4f32-9b0c-38b864dd6aec\n\nIt is combination of two tools:\n1. JADX-AI-MCP\n2. [JADX MCP SERVER](https://github.com/zinja-coder/jadx-mcp-server)\n\n## 🤖 What is JADX-MCP-SERVER?\n\n**JADX MCP Server** is a standalone Python server that interacts with a `JADX-AI-MCP` plugin (see: [jadx-ai-mcp](https://github.com/zinja-coder/jadx-ai-mcp)) via MCP (Model Context Protocol). It lets LLMs communicate with the decompiled Android app context live.\n\n---\n\n## Other projects in Zin MCP Suite\n - **[APKTool-MCP-Server](https://github.com/zinja-coder/apktool-mcp-server)**\n - **[JADX-MCP-Server](https://github.com/zinja-coder/jadx-mcp-server)**\n - **[ZIN-MCP-Client](https://github.com/zinja-coder/zin-mcp-client)**\n\n## Current MCP Tools\n\nThe following MCP tools are available:\n\n- `fetch_current_class()` — Get the class name and full source of selected class\n- `get_selected_text()` — Get currently selected text\n- `get_all_classes()` — List all classes in the project\n- `get_class_source()` — Get full source of a given class\n- `get_method_by_name()` — Fetch a method's source\n- `search_method_by_name()` — Search method across classes\n- `search_classes_by_keyword()` — Search for classes whose source code contains a specific keyword (supports pagination)\n- `get_methods_of_class()` — List methods in a class\n- `get_fields_of_class()` — List fields in a class\n- `get_smali_of_class()` — Fetch smali of class\n- `get_main_activity_class()` — Fetch main activity from jadx mentioned in AndroidManifest.xml file.\n- `get_main_application_classes_code()` — Fetch all the main application classes' code based on the package name defined in the AndroidManifest.xml.\n- `get_main_application_classes_names()` — Fetch all the main application classes' names based on the package name defined in the AndroidManifest.xml.\n- `get_android_manifest()` — Retrieve and return the AndroidManifest.xml content.\n- `get_strings()` : Fetches the strings.xml file\n- `get_all_resource_file_names()` : Retrieve all resource files names that exists in application\n- `get_resource_file()` : Retrieve resource file content\n- `rename_class()` : Renames the class name\n- `rename_method()` : Renames the method\n- `rename_field()` : Renames the field\n- `rename_package()` : Renames whole package\n- `rename_variable()` : Renames the variable within a method\n- `debug_get_stack_frames()` : Get the stack frames from jadx debugger\n- `debug_get_threads()` : Get the insights of threads from jadx debugger\n- `debug_get_variables()` : Get the variables from jadx debugger\n- `xrefs_to_class()` : Find all references to a class (returns method-level and class-level references, supports pagination)\n- `xrefs_to_method()` : Find all references to a method (includes override-related methods, supports pagination)\n- `xrefs_to_field()` : Find all references to a field (returns methods that access the field, supports pagination)\n  \n---\n\n## 🗒️ Sample Prompts\n\n🔍 Basic Code Understanding\n\n    \"Explain what this class does in one paragraph.\"\n\n    \"Summarize the responsibilities of this method.\"\n\n    \"Is there any obfuscation in this class?\"\n\n    \"List all Android permissions this class might require.\"\n\n🛡️ Vulnerability Detection\n\n    \"Are there any insecure API usages in this method?\"\n\n    \"Check this class for hardcoded secrets or credentials.\"\n\n    \"Does this method sanitize user input before using it?\"\n\n    \"What security vulnerabilities might be introduced by this code?\"\n\n🛠️ Reverse Engineering Helpers\n\n    \"Deobfuscate and rename the classes and methods to something readable.\"\n\n    \"Can you infer the original purpose of this smali method?\"\n\n    \"What libraries or SDKs does this class appear to be part of?\"\n\n    \"Tell me which classes contains code related to 'encryption'?\"\n\n📦 Static Analysis\n\n    \"List all network-related API calls in this class.\"\n\n    \"Identify file I/O operations and their potential risks.\"\n\n    \"Does this method leak device info or PII?\"\n\n🤖 AI Code Modification\n\n    \"Refactor this method to improve readability.\"\n\n    \"Add comments to this code explaining each step.\"\n\n    \"Rewrite this Java method in Python for analysis.\"\n\n📄 Documentation \u0026 Metadata\n\n    \"Generate Javadoc-style comments for all methods.\"\n\n    \"What package or app component does this class likely belong to?\"\n\n    \"Can you identify the Android component type (Activity, Service, etc.)?\"\n\n🐞 Debugger Assistant\n```\n   \"Fetch stack frames, varirables and threads from debugger and provide summary\"\n\n   \"Based the stack frames from debugger, explain the execution flow of the application\"\n\n   \"Based on the state of variables, is there security threat?\"\n```\n\n---\n\n## 🛠️ Getting Started \n\n### 1. Download from Releases: https://github.com/zinja-coder/jadx-ai-mcp/releases\n\n\u003e [!NOTE]\n\u003e\n\u003e Download both `jadx-ai-mcp-\u003cversion\u003e.jar` and `jadx-mcp-server-\u003cversion\u003e.zip` files.\n\n\n```bash\n# 0. Download the jadx-ai-mcp-\u003cversion\u003e.jar and jadx-mcp-server-\u003cversion\u003e.zip\nhttps://github.com/zinja-coder/jadx-ai-mcp/releases\n\n# 1. \nunzip jadx-ai-mcp-\u003cversion\u003e.zip\n\n├jadx-mcp-server/\n  ├── jadx_mcp.py\n  ├── requirements.txt\n  ├── README.md\n  ├── LICENSE\n\n├jadx-ai-mcp-\u003cversion\u003e.jar\n\n# 2. Install the plugin\n\n# For this you can follow two approaches:\n\n## 1. One liner - execute below command in your shell\njadx plugins --install \"github:zinja-coder:jadx-ai-mcp\"\n\n## The above one line code will install the latest version of the plugin directly into the jadx, no need to download the jadx-ai-mcp's .jar file.\n## 2. Or you can use JADX-GUI to install it by following images as shown below:\n```\n\n\u003cdiv align=\"center\"\u003e\n    \u003cimg alt=\"banner\" height=\"480px\" widht=\"620px\" src=\"docs/assets/img_1231.png\"\u003e\n\u003c/div\u003e\n\n\u003cdiv align=\"center\"\u003e\n    \u003cimg alt=\"banner\" height=\"480px\" widht=\"620px\" src=\"docs/assets/img_1123.png\"\u003e\n\u003c/div\u003e\n\n\u003cdiv align=\"center\"\u003e\n    \u003cimg alt=\"banner\" height=\"480px\" widht=\"620px\" src=\"docs/assets/img_2122.png\"\u003e\n\u003c/div\u003e\n\n\n```bash\n## 3. GUI method, download the .jar file and follow below steps shown in images\n```\n![img.png](docs/assets/img123.png)\n![img_1.png](docs/assets/img_12.png)\n![img_2.png](docs/assets/img_2.png)\n![img_3.png](docs/assets/img_3.png)\n```bash\n# 3. Navigate to jadx-mcp-server directory\ncd jadx-mcp-server\n\n# 4. This project uses uv - https://github.com/astral-sh/uv instead of pip for dependency management.\n    ## a. Install uv (if you dont have it yet)\ncurl -LsSf https://astral.sh/uv/install.sh | sh\n    ## b. OPTIONAL, if for any reasons, you get dependecy errors in jadx-mcp-server, Set up the environment\nuv venv\nsource .venv/bin/activate  # or .venv\\Scripts\\activate on Windows\n    ## c. OPTIONAL Install dependencies\nuv pip install httpx fastmcp\n\n# The setup for jadx-ai-mcp and jadx_mcp_server is done.\n```\n\n## 🤖 2. Use Claude Desktop\n\nMake sure Claude Desktop is running with MCP enabled.\n\nFor instance, I have used following for Kali Linux: https://github.com/aaddrick/claude-desktop-debian\n\nConfigure and add MCP server to LLM file:\n```bash\nnano ~/.config/Claude/claude_desktop_config.json\n```\n\nFor:\n   - Windows: `%APPDATA%\\Claude\\claude_desktop_config.json`\n   - macOS: `~/Library/Application Support/Claude/claude_desktop_config.json`\n   \nAnd following content in it:\n```json\n{\n    \"mcpServers\": {\n        \"jadx-mcp-server\": {\n            \"command\": \"/\u003cpath\u003e/\u003cto\u003e/uv\", \n            \"args\": [\n                \"--directory\",\n                \"\u003c/PATH/TO/\u003ejadx-mcp-server/\",\n                \"run\",\n                \"jadx_mcp_server.py\"\n            ]\n        }\n    }\n}\n```\n\nReplace:\n\n- `path/to/uv` with the actual path to your `uv` executable\n- `path/to/jadx-mcp-server` with the absolute path to where you cloned this\nrepository\n\nThen, navigate code and interact via real-time code review prompts using the built-in integration.\n\n**OR**\n\nor you can install the jadx_mcp_server directly as executable directly using below command:\n\n```\nuv tool install git+https://github.com/zinja-coder/jadx-mcp-server\n```\n\nand then you can just provide `jadx_mcp_server` in `command` section of mcp configuration.\n\n## 3. Use Cherry Studio\n\nIf you want to configure the MCP tool in Cherry Studio, you can refer to the following configuration.\n- Type: stdio\n- command: uv\n- argument:\n```bash\n--directory\npath/to/jadx-mcp-server\nrun\njadx_mcp_server.py\n```\n- `path/to/jadx-mcp-server` with the absolute path to where you cloned this\nrepository\n\n## 4. Using LMStudio\n\nYou can also use JADX AI MCP Server with LM Studio by configuring it's mcp.json file. Here's the video guide.\n\nhttps://github.com/user-attachments/assets/b4a6b280-5aa9-4e76-ac72-a0abec73b809\n\n## 5. Running in HTTP Stream Mode\n\nYou can also use Jadx in HTTP Stream Mode using `--http` option with `jadx_mcp_server.py` as shown in following:\n\n```bash\nuv run jadx_mcp_server.py --http\n\nOR\n\nuv run jadx_mcp_server.py --http --port 9999\n```\n\n## 6. Custom port configuration for JADX AI MCP Plugin\n\n\u003cimg width=\"800\" height=\"335\" alt=\"image\" src=\"https://github.com/user-attachments/assets/6243adc5-5be4-4e2d-aa16-bdaf78a28e36\" /\u003e\n\n1. Configure Port: Configure the port on which the JADX AI MCP Plugin will listen on.\n2. Default Port: Revert back the changes and listen on default port.\n3. Restart Server: Force restart the JADX AI MCP Plugin server.\n4. Server Status: Check the status of JADX AI MCP Plugin server.\n\nTo connect with JADX AI MCP Plugin running on custom port, the `--jadx-port` option will be used as shown in following:\n```\nuv run jadx_mcp_server.py --jadx-port 8652\n```\n\nThe MCP Configuration for above will be as follows for claude:\n\n```\n{\n  \"mcpServers\": {\n    \"jadx-mcp-server\": {\n      \"command\": \"/path/to/uv\",\n      \"args\": [\n        \"--directory\",\n        \"/path/to/jadx-mcp-server/\",\n        \"run\",\n        \"jadx_mcp_server.py\",\n        \"--jadx-port\",\n        \"8652\"\n      ]\n    }\n  }\n}\n```\n\n## Give it a shot\n\n1. Run jadx-gui and load any .apk file\n\n![img_1.png](docs/assets/img_1.png)\n\n2. Start claude - You must see hammer symbol\n\n![img2.png](docs/assets/img2.png)\n\n3. Click on the `hammer` symbol and you should you see somthing like following:\n\n![img3.png](docs/assets/img3.png)\n\n4. Run following prompt:\n```text\nfetch currently selected class and perform quick sast on it\n```\n![img4.png](docs/assets/img4.png)\n\n5. Allow access when prompted:\n\n![img_1.png](docs/assets/img5.png)\n\n6. HACK!\n\n![img_2.png](docs/assets/img6.png)\n\nThis plugin allows total control over the GUI and internal project model to support deeper LLM integration, including:\n\n- Exporting selected class to MCP\n- Running automated Claude analysis\n- Receiving back suggestions inline\n\n---\n\n## Troubleshooting\n\n[Check here](https://github.com/zinja-coder/jadx-ai-mcp/edit/jadx-ai/TROUBLESHOOTING.md)\n\n## NOTE For Contributors\n\n - The files related to JADX-AI-MCP can be found under this repo.\n\n - The files related to **jadx-mcp-server** can be found [here](https://github.com/zinja-coder/jadx-mcp-server).\n\n## To report bugs, issues, feature suggestion, Performance issue, general question, Documentation issue.\n - Kindly open an issue with respective template.\n\n - Tested on Claude Desktop Client, support for other AI will be tested soon!\n\n## 🙏 Credits\n\nThis project is a plugin for JADX, an amazing open-source Android decompiler created and maintained by [@skylot](https://github.com/skylot). All core decompilation logic belongs to them. I have only extended it to support my MCP server with AI capabilities.\n\n[📎 Original README (JADX)](https://github.com/skylot/jadx)\n\nThe original README.md from jadx is included here in this repository for reference and credit.\n\nThis MCP server is made possible by the extensibility of JADX-GUI and the amazing Android reverse engineering community.\n\nAlso huge thanks to [@aaddrick](https://github.com/aaddrick) for developing Claude desktop for Debian based linux.\n\nAnd in last thanks to [@anthropics](https://github.com/anthropics) for developing the Model Context Protocol and [@FastMCP](https://github.com/modelcontextprotocol/python-sdk) team\n\nApart from this, huge thanks to all open source projects which serve as a dependencies for this project and which made this possible.\n\n### Dependencies\n\nThis project uses following awesome libraries.\n\n- Plugin - Java\n  - Javalin     - https://javalin.io/ - Apache 2.0 License\n  - SLF4J       - https://slf4j.org/  - MIT License\n  - org.w3c.dom - https://mvnrepository.com/artifact/org.w3c.dom - W3C Software and Document License\n\n- MCP Server - Python\n  - FastMCP - https://github.com/jlowin/fastmcp - Apache 2.0 License\n  - httpx   - https://www.python-httpx.org      - BSD-3-Clause (“BSD licensed”) \n\n## 📄 License\n\nJADX-AI-MCP and all related projects inherits the Apache 2.0 License from the original JADX repository.\n\n## ⚖️ Legal Warning\n\n**Disclaimer**\n\nThe tools `jadx-ai-mcp` and `jadx_mcp_server` are intended strictly for educational, research, and ethical security assessment purposes. They are provided \"as-is\" without any warranties, expressed or implied. Users are solely responsible for ensuring that their use of these tools complies with all applicable laws, regulations, and ethical guidelines.\n\nBy using `jadx-ai-mcp` or `jadx_mcp_server`, you agree to use them only in environments you are authorized to test, such as applications you own or have explicit permission to analyze. Any misuse of these tools for unauthorized reverse engineering, infringement of intellectual property rights, or malicious activity is strictly prohibited.\n\nThe developers of `jadx-ai-mcp` and `jadx_mcp_server` shall not be held liable for any damage, data loss, legal consequences, or other consequences resulting from the use or misuse of these tools. Users assume full responsibility for their actions and any impact caused by their usage.\n\nUse responsibly. Respect intellectual property. Follow ethical hacking practices.\n\n---\n\n## 🙌 Contribute or Support\n\n- Found it useful? Give it a ⭐️\n- Got ideas? Open an [issue](https://github.com/zinja-coder/jadx-ai-mcp/issues) or submit a PR\n- Built something on top? DM me or mention me — I’ll add it to the README!\n- Do you like my work and keep it going? Sponsor this project.\n  \n---\n\nBuilt with ❤️ for the reverse engineering and AI communities.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fzinja-coder%2Fjadx-ai-mcp","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fzinja-coder%2Fjadx-ai-mcp","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fzinja-coder%2Fjadx-ai-mcp/lists"}