Frida
About
Enables dynamic instrumentation of mobile and desktop applications through Frida toolkit, providing capabilities for process management, device enumeration, and script injection for application analysis and debugging workflows.
Details
- Author
- dnakov
- Repository
- dnakov/frida-mcp
- GitHub stars
- 34
- Downloads
- 2,250
- License
- MIT License
- Categories
- Productivity, Design, Developer Tools, AI, Infrastructure, Other
- Tags
- #integration
Jump to
- Process management: list, attach, spawn, resume, and kill
- Device management: USB and remote device support
- Interactive JavaScript REPL with real-time execution
- Script injection with progress tracking
- Resources for providing Frida data to models
- Prompts for guided Frida analysis workflows
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
FridaCommand (node, npx, python, etc.)frida-mcpPlease refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
Install via pip with pip install frida-mcp. For Claude Desktop integration, add frida-mcp as an MCP server in the Claude Desktop configuration file with the command "frida-mcp".
list_processes
List all running processes.
attach_process
Attach to a specific process.
spawn_process
Spawn a new process.
resume_process
Resume a suspended process.
kill_process
Kill a specific process.
list_devices
List all connected devices (USB, remote).
get_device_info
Get information about a specific device.
connect_device
Connect to a specific device.
create_repl_session
Create an interactive session with a process.
execute_js_code
Execute JavaScript code in real-time.
monitor_process_state
Monitor the state and memory of a process.
hook_functions
Hook functions and intercept calls.
capture_console_output
Capture console.log output.
handle_errors
Handle errors and exceptions gracefully.
inject_script
Inject custom JavaScript scripts.
track_injection_progress
Track the progress of script injection.
handle_script_errors
Handle errors and exceptions during script execution.
get_frida_version
Get Frida version information.
get_process_list
Access the process list in a human-readable format.
get_device_list
Access the device list in a human-readable format.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"frida": {
"cwd": "string",
"env": {},
"args": [],
"shell": false,
"command": "frida-mcp"
}
}
}Linux
{
"cwd": "string",
"env": [],
"args": [],
"shell": false,
"command": "frida-mcp"
}Macos
{
"cwd": "string",
"env": [],
"args": [],
"shell": false,
"command": "frida-mcp"
}Windows
{
"cwd": "string",
"env": [],
"args": [],
"shell": false,
"command": "frida-mcp"
}Frida MCP
A Model Context Protocol (MCP) implementation for Frida dynamic instrumentation toolkit.
Overview
This package provides an MCP-compliant server for Frida, enabling AI systems to interact with mobile and desktop applications through Frida's dynamic instrumentation capabilities. It uses the official MCP Python SDK to enable seamless integration with AI applications.
Demo
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
