ya-frida-mcp
A comprehensive MCP server for Frida dynamic instrumentation, enabling AI agents to manage devices, processes, scripts, memory, and ADB operations.
README
WIP: Ya Frida MCP
Pending JsBridge fix #3
<p align="center"> <img src="https://socialify.git.ci/1shin-7/ya-frida-mcp/image?description=1&font=Inter&language=1&name=1&owner=1&pattern=Plus&theme=Auto" alt="ya-frida-mcp" width="640" /> </p>
<p align="center"> <a href="https://github.com/1shin-7/ya-frida-mcp/actions"><img src="https://img.shields.io/github/actions/workflow/status/1shin-7/ya-frida-mcp/ci.yml?style=flat-square" alt="CI" /></a> <a href="https://pypi.org/project/ya-frida-mcp/"><img src="https://img.shields.io/pypi/v/ya-frida-mcp?style=flat-square&color=blue" alt="PyPI" /></a> <a href="https://pypi.org/project/ya-frida-mcp/"><img src="https://img.shields.io/pypi/pyversions/ya-frida-mcp?style=flat-square" alt="Python" /></a> <a href="https://github.com/1shin-7/ya-frida-mcp/blob/main/LICENSE"><img src="https://img.shields.io/github/license/1shin-7/ya-frida-mcp?style=flat-square" alt="License" /></a> <a href="https://github.com/1shin-7/ya-frida-mcp/stargazers"><img src="https://img.shields.io/github/stars/1shin-7/ya-frida-mcp?style=flat-square" alt="Stars" /></a> </p>
<p align="center"><b>Yet Another Frida MCP Server</b> — Full-featured <a href="https://modelcontextprotocol.io">MCP</a> server for <a href="https://frida.re">Frida</a> dynamic instrumentation.</p>
<p align="center">English | <a href="README.zh-CN.md">简体中文</a></p>
Existing Frida MCP servers on the market are either abandoned, poorly maintained, or limited to a handful of basic operations. ya-frida-mcp was built from scratch to be a comprehensive, production-ready bridge between AI agents and Frida — covering device management, process control, script injection, memory operations, and even ADB integration out of the box.
Features
59 MCP tools across 7 categories, all returning structured JSON for minimal token consumption.
| Category | Tools | Highlights |
|---|---|---|
| Device | frida_ls_devices frida_get_device frida_add_remote frida_remove_remote frida_query_system_parameters frida_enable_spawn_gating frida_disable_spawn_gating frida_enumerate_pending_spawn frida_enumerate_pending_children frida_inject_library_file frida_inject_library_blob |
Device management, system info, spawn gating, native library injection |
| Process | frida_ps frida_spawn frida_attach frida_detach frida_kill frida_resume frida_list_sessions |
Full process lifecycle; frida_ps supports scope/pids, frida_spawn supports argv/env/cwd/stdio |
| App | frida_ls_apps frida_ls_apps_running frida_get_frontmost_application |
App enumeration with scope/identifiers filtering |
| Script | frida_inject frida_rpc_call frida_unload_script frida_get_messages frida_list_scripts frida_enumerate_modules frida_enumerate_exports frida_list_exports frida_post_message frida_enable_child_gating frida_disable_child_gating frida_compile_script frida_snapshot_script frida_eternalize_script |
JS injection (QJS/V8), RPC, child gating, bytecode compilation, script snapshots |
| Memory | frida_memory_read frida_memory_write frida_memory_scan frida_memory_protect |
Read/write/scan/protect with hex I/O |
| ADB (optional) | adb_shell adb_push adb_pull adb_install adb_logcat adb_forward adb_root ... |
17 tools, auto-registered when adb is on PATH |
| Frida Server (optional) | frida_server_status frida_server_install frida_server_start frida_server_stop |
Auto-download, push, and manage frida-server on Android via ADB |
Also includes:
- MCP Resources — live device list, session state, process/app enumeration as subscribable resources
- MCP Prompts — workflow templates for native hooking, Java/ObjC hooking, Stalker tracing, module dumping
- TOML Configuration — customize transport, default device, remote devices, timeouts
- CLI Utilities —
doctor,devices,ps,ls,tools,install/uninstallfor MCP clients - One-command client setup — register into 22+ MCP clients including Claude Desktop, Cursor, VS Code, Windsurf, Roo Code, Cline, Kiro, and more
- Structured output — all tools return compact JSON with
Literaltype hints for LLM-friendly schemas
Quickstart
Install
# PyPI (recommended)
pip install ya-frida-mcp
# Or via uv
uv tool install ya-frida-mcp
Register into your MCP client
# Pick your client
ya-frida-mcp install claude-desktop
ya-frida-mcp install cursor
ya-frida-mcp install vscode
ya-frida-mcp install windsurf
ya-frida-mcp install roo-code
ya-frida-mcp install cline
# All supported clients at once
ya-frida-mcp install all
<details> <summary>All supported clients (22)</summary>
| Key | Client |
|---|---|
amazon-q |
Amazon Q Developer CLI |
augment-code |
Augment Code |
claude-desktop |
Claude Desktop |
claude-code |
Claude Code |
cline |
Cline |
copilot-cli |
Copilot CLI |
crush |
Crush |
cursor |
Cursor |
gemini-cli |
Gemini CLI |
kilo-code |
Kilo Code |
kiro |
Kiro |
lm-studio |
LM Studio |
opencode |
Opencode |
qodo-gen |
Qodo Gen |
qwen-coder |
Qwen Coder |
roo-code |
Roo Code |
trae |
Trae |
vscode |
VS Code |
vscode-insiders |
VS Code Insiders |
warp |
Warp |
windsurf |
Windsurf |
zed |
Zed |
</details>
Start the server manually
# stdio (default, used by MCP clients)
ya-frida-mcp serve
# SSE transport
ya-frida-mcp serve -t sse -H 0.0.0.0 -p 8000
Configuration (optional)
ya-frida-mcp init-config # generates config.toml in current directory
ya-frida-mcp show-config # display resolved config
ya-frida-mcp -c /path/to/config.toml serve
# config.toml
[server]
name = "ya-frida-mcp"
transport = "stdio" # "stdio" or "sse"
host = "127.0.0.1"
port = 8000
[frida]
default_device = "local" # "local", "usb", or device ID
script_timeout = 10
spawn_timeout = 15
[[frida.remote_devices]]
host = "192.168.1.100"
port = 27042
CLI Reference
ya-frida-mcp doctor # diagnose Frida connectivity
ya-frida-mcp devices # list Frida devices
ya-frida-mcp ps # list running processes (frida-ps)
ya-frida-mcp ls # list installed apps (frida-ls)
ya-frida-mcp tools # list all registered MCP tools
ya-frida-mcp version # show version info
Development
# Clone
git clone https://github.com/1shin-7/ya-frida-mcp.git
cd ya-frida-mcp
# Install dependencies
uv sync
# Run in dev mode
uv run ya-frida-mcp serve
# Lint
uv run ruff check ya_frida_mcp/
# List tools (verify registration)
uv run ya-frida-mcp tools
Project Structure
ya_frida_mcp/
├── cli.py # Click CLI entry point
├── config.py # TOML configuration management
├── installer.py # MCP client config installers
├── server.py # FastMCP server factory + lifespan
├── resources.py # MCP resources
├── prompts.py # MCP workflow prompts
├── core/
│ ├── base.py # ABC base classes + async helpers
│ ├── device.py # Frida device wrapper + manager
│ ├── session.py # Session + script lifecycle
│ ├── adb.py # ADB CLI async wrapper
│ ├── frida_server.py # frida-server download & deploy logic
│ └── output.py # Structured output helpers
└── tools/
├── device.py # Device discovery tools
├── process.py # Process management tools
├── app.py # App enumeration tools
├── script.py # Script injection + RPC tools
├── memory.py # Memory read/write/scan tools
├── adb.py # ADB CLI tools (optional)
└── frida_server.py # frida-server management tools (optional)
Credits
- Frida — Dynamic instrumentation toolkit
- FastMCP — Pythonic MCP server framework
- Click — CLI framework
- Claude — AI-assisted development
License
推荐服务器
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。
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。
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。
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。
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。
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。
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。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
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。