使用说明
WIP：Ya Frida MCP
等待JsBridge修复 #3
Yet Another Frida MCP Server — Full-featured MCP server for Frida dynamic instrumentation.
English | 简体中文
市场上现有的Frida MCP服务器要么被废弃，要么维护不善，要么仅限于少数基本操作。 的 frida-mcp 从零开始构建，成为AI代理和Frida之间全面的、生产就绪的桥梁，涵盖设备管理、过程控制、脚本注入、内存操作，甚至开箱即用的ADB集成。
特性
59个MCP工具 在7个类别中，所有类别都返回结构化JSON，以实现最小的令牌消耗。
| 类别 | 工具 | 亮点 |
|---|---|---|
| 设备 | 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 |
设备管理、系统信息、生成门控、本机库注入 |
| 过程 | frida_ps frida_spawn frida_attach frida_detach frida_kill frida_resume frida_list_sessions |
全过程生命周期； frida_ps 支持范围/pids， frida_spawn 支持argv/env/cwd/stdio |
| 应用 | frida_ls_apps frida_ls_apps_running frida_get_frontmost_application |
具有范围/标识符过滤的应用程序枚举 |
| 脚本 | 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注入（QJS/V8）、RPC、子门控、字节码编译、脚本快照 |
| 记忆 | frida_memory_read frida_memory_write frida_memory_scan frida_memory_protect |
使用十六进制I/O进行读/写/扫描/保护 |
| ADB公司 （可选） | adb_shell adb_push adb_pull adb_install adb_logcat adb_forward adb_root … |
17个工具，在以下情况下自动注册 adb 在PATH上 |
| Frida服务器 （可选） | frida_server_status frida_server_install frida_server_start frida_server_stop |
通过ADB在Android上自动下载、推送和管理frida服务器 |
还包括：
- MCP资源 --作为可订阅资源的实时设备列表、会话状态、进程/应用程序枚举
- MCP提示 --用于原生挂钩、Java/ObjC挂钩、跟踪、模块转储的工作流模板
- TOML配置 --自定义传输、默认设备、远程设备、超时
- CLI实用程序 —
doctor,devices,ps,ls,tools,install/uninstall对于MCP客户 - 单命令客户端设置 --注册到22多个MCP客户端，包括Claude Desktop、Cursor、VS Code、Windsurf、Roo Code、Cline、Kiro等
- 结构化输出 --所有工具都返回紧凑的JSON
LiteralLLM友好模式的类型提示
快速入门
安装
# PyPI (recommended)
pip install ya-frida-mcp
# Or via uv
uv tool install ya-frida-mcp
注册到您的MCP客户端
# 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
All supported clients (22)
| 密钥 | 客户端 |
|---|---|
amazon-q |
Amazon Q开发者命令行界面 |
augment-code |
增强代码 |
claude-desktop |
克劳德桌面 |
claude-code |
克劳德代码 |
cline |
克莱恩 |
copilot-cli |
Copilot命令行界面 |
crush |
粉碎 |
cursor |
光标 |
gemini-cli |
Gemini CLI |
kilo-code |
基洛代码 |
kiro 基罗 |
|
lm-studio |
LM工作室 |
opencode |
开放代码 |
qodo-gen |
Qodo Gen |
qwen-coder |
Qwen编码器 |
roo-code |
Roo代码 |
trae |
带来 |
vscode |
VS代码 |
vscode-insiders |
VS代码内部人员 |
warp |
翘曲 |
windsurf |
风帆冲浪 |
zed |
Zed |
手动启动服务器
# 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
配置（可选）
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参考
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
发展
# 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
项目结构
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)
