Frida MCP Server

Frida MCP Server

A comprehensive MCP server that exposes Frida's dynamic instrumentation toolkit to AI agents for process management, script injection, and memory operations. It provides over 50 tools to interact with local and mobile devices, enabling advanced capabilities like function hooking and memory analysis.

Category
访问服务器

README

Frida MCP Server

A comprehensive MCP (Model Context Protocol) server that exposes the full power of Frida's dynamic instrumentation toolkit to AI agents.

Features

55 tools covering all major Frida capabilities:

Device & Process Management

  • frida_list_devices - List all available Frida devices
  • frida_get_device_info - Get detailed device information
  • frida_list_processes - List running processes
  • frida_list_applications - List installed applications
  • frida_get_process - Get process details by name/PID
  • frida_spawn - Spawn a new process (suspended)
  • frida_resume - Resume a spawned process
  • frida_kill - Kill a process

Session Management

  • frida_attach - Attach to a running process
  • frida_detach - Detach from a session

Script Injection

  • frida_inject_script - Inject and run JavaScript in a process
  • frida_unload_script - Unload an injected script
  • frida_rpc_call - Call RPC functions in scripts
  • frida_evaluate - Evaluate arbitrary JavaScript

Function Hooking

  • frida_hook_function - Hook native functions
  • frida_intercept_method - Intercept ObjC/Java methods
  • frida_trace - Trace function calls with patterns

Memory Operations

  • frida_memory_scan - Scan memory for patterns
  • frida_memory_read - Read bytes from memory
  • frida_memory_write - Write bytes to memory
  • frida_search_strings - Search for strings in memory

Module Enumeration

  • frida_list_modules - List loaded modules
  • frida_list_exports - List module exports
  • frida_list_imports - List module imports
  • frida_resolve_exports - Find functions by pattern (ApiResolver)

Java (Android)

  • frida_java_enumerate_classes - List Java classes
  • frida_java_hook_method - Hook Java methods
  • frida_java_find_instances - Find class instances on heap
  • frida_java_call_method - Call Java methods

Objective-C (iOS/macOS)

  • frida_objc_enumerate_classes - List ObjC classes
  • frida_objc_hook_method - Hook ObjC methods
  • frida_objc_find_instances - Find class instances on heap

Advanced

  • frida_stalker_trace - Instruction-level tracing
  • frida_inject_library - Inject shared libraries
  • frida_enable_spawn_gating - Intercept new processes
  • frida_disable_spawn_gating - Disable spawn gating
  • frida_get_pending_spawn - Get pending spawned processes
  • frida_get_process_info - Detailed process information

File Operations

  • frida_pull_file - Download file from device
  • frida_push_file - Upload file to device

Installation

# Install dependencies
pip3 install frida frida-tools mcp

# Or with --break-system-packages on newer Ubuntu
pip3 install --break-system-packages frida frida-tools mcp

Usage

As stdio MCP server

python3 server.py

Example MCP configuration

{
  "mcpServers": {
    "frida": {
      "command": "python3",
      "args": ["/path/to/frida-mcp/server.py"]
    }
  }
}

Example Workflows

1. List processes and attach

1. Call frida_list_processes to see running processes
2. Call frida_attach with target="processName" or target=1234 (PID)
3. Use the returned session_id for further operations

2. Hook a function

1. frida_attach to the target process
2. frida_hook_function with the session_id, function name, and optional onEnter/onLeave code
3. Observe the script_id and retrieve logs with frida_unload_script when done

3. Trace SSL/crypto calls

1. frida_attach to a network application
2. frida_trace with include=["*SSL*", "*crypto*"] to see all SSL-related calls

4. Android app analysis

1. frida_list_applications on USB device to find the app
2. frida_attach to the app
3. frida_java_enumerate_classes to explore classes
4. frida_java_hook_method to intercept specific methods
5. frida_java_find_instances to find live objects

5. Memory forensics

1. frida_attach to the target process
2. frida_search_strings to find interesting strings
3. frida_memory_read to dump specific memory regions
4. frida_memory_scan for byte patterns

Device Types

  • local - Local system (default)
  • usb - USB-connected device (Android/iOS with frida-server)
  • remote - Remote frida-server over TCP

Requirements

  • Python 3.8+
  • Frida 16.0+ (pip install frida frida-tools)
  • MCP SDK (pip install mcp)

For mobile device support:

  • Android: Install frida-server on the device
  • iOS: Install frida via jailbreak or use frida-gadget

Security Notes

⚠️ Frida is a powerful tool that can be used for both security research and malicious purposes. Only use on systems you own or have explicit permission to test.

License

MIT

Memory Management (NEW)

  • frida_memory_alloc - Allocate memory in target process
  • frida_memory_protect - Change memory page permissions
  • frida_enumerate_ranges - List memory ranges/maps

Thread Operations (NEW)

  • frida_enumerate_threads - List all threads with state
  • frida_backtrace - Get stack backtrace

Symbol Resolution (NEW)

  • frida_debug_symbol - Resolve symbols from address/name
  • frida_list_symbols - List debug symbols from module

Native Calling (NEW)

  • frida_native_function - Call native functions directly
  • frida_cmodule - Compile and load inline C code

ObjC Extended (NEW)

  • frida_objc_call_method - Call ObjC methods on class/instance

Java Extended (NEW)

  • frida_java_load_dex - Load DEX files dynamically

Network (NEW)

  • frida_socket_connect - Create socket connections from process

推荐服务器

Baidu Map

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。

官方
精选
JavaScript
Playwright MCP Server

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。

官方
精选
TypeScript
Magic Component Platform (MCP)

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。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

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。

官方
精选
本地
TypeScript
VeyraX

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。

官方
精选
本地
graphlit-mcp-server

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。

官方
精选
TypeScript
Kagi MCP Server

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。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

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。

官方
精选