Skip to content
Back to search

frida-mcp

MCP stdio server for frida

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/dnakov--frida-mcp/badge.svg)](/listings/dnakov--frida-mcp)

HTML

<a href="/listings/dnakov--frida-mcp"><img src="/api/listings/dnakov--frida-mcp/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

Prerequisites

- Python 3.8 or later - pip package manager - Frida 16.0.0 or later

Quick Install

pip install frida-mcp

Development Install

# Clone the repository
git clone https://github.com/yourusername/frida-mcp.git
cd frida-mcp

# Install in development mode with extra tools
pip install -e ".[dev]"

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 123 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. # Frida MCP
  2. A Model Context Protocol (MCP) implementation for Frida dynamic instrumentation toolkit.
  3. ## Overview
  4. 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](https://github.com/modelcontextprotocol/python-sdk) to enable seamless integration with AI applications.
  5. ## Demo
  6. https://github.com/user-attachments/assets/5dc0e8f5-5011-4cf2-be77-6a77ec960501
  7. ## Features
  8. - Built with the official MCP Python SDK
  9. - Comprehensive Frida tools exposed through MCP:
  10. - Process management (list, attach, spawn, resume, kill)
  11. - Device management (USB, remote devices)
  12. - Interactive JavaScript REPL with real-time execution
  13. - Script injection with progress tracking
  14. - Process and device monitoring
  15. - Resources for providing Frida data to models
  16. - Prompts for guided Frida analysis workflows
  17. - Progress tracking for long-running operations
  18. - Full support for all MCP transport methods
  19. ## Installation
  20. ### Prerequisites
  21. - Python 3.8 or later
  22. - pip package manager
  23. - Frida 16.0.0 or later
  24. ### Quick Install
  25. ```bash
  26. pip install frida-mcp
  27. ```
  28. ### Development Install
  29. ```bash
  30. # Clone the repository
  31. git clone https://github.com/yourusername/frida-mcp.git
  32. cd frida-mcp
  33. # Install in development mode with extra tools
  34. pip install -e ".[dev]"
  35. ```
  36. ## Claude Desktop Integration
  37. To use Frida MCP with Claude Desktop, you'll need to update your Claude configuration file:
  38. 1. Locate your Claude Desktop configuration file:
  39. - macOS: `~/Library/Application Support/Claude/claude_desktop_config.json`
  40. - Windows: `%APPDATA%\Claude\claude_desktop_config.json`
  41. - Linux: `~/.config/Claude/claude_desktop_config.json`
  42. 2. Add the following to your configuration file:
  43. ```json
  44. {
  45. "mcpServers": {
  46. "frida": {
  47. "command": "frida-mcp"
  48. }
  49. }
  50. }
  51. ```
  52. ## Usage
  53. Once installed, you can use Frida MCP directly from Claude Desktop. The server provides the following capabilities:
  54. ### Process Management
  55. - List all running processes
  56. - Attach to specific processes
  57. - Spawn new processes
  58. - Resume suspended processes
  59. - Kill processes
  60. ### Device Management
  61. - List all connected devices (USB, remote)
  62. - Get device information
  63. - Connect to specific devices
  64. ### Interactive JavaScript REPL
  65. - Create interactive sessions with processes
  66. - Execute JavaScript code in real-time
  67. - Monitor process state and memory
  68. - Hook functions and intercept calls
  69. - Capture console.log output
  70. - Handle errors and exceptions gracefully
  71. ### Script Injection
  72. - Inject custom JavaScript scripts
  73. - Track injection progress
  74. - Handle script errors and exceptions
  75. ### Resources
  76. - Get Frida version information
  77. - Access process list in human-readable format
  78. - Access device list in human-readable format
  79. ## Development
  80. ```bash
  81. # Clone repository
  82. git clone https://github.com/yourusername/frida-mcp.git
  83. cd frida-mcp
  84. # Install development dependencies
  85. pip install -e ".[dev]"
  86. ```
  87. ## License
  88. MIT

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.