Atlas / MCP servers / 0xhackerfren / Frida Game Hacking

Frida Game HackingBLOCK

Name: Frida Game Hacking
Author: 0xhackerfren

mcp/0xhackerfren/frida-game-hacking

MCP server by 0xhackerfren · Audited 2026-10-07

A MCP implementation of Frida that seeks to emulate Cheat Engine functionally to allow for seamless Game Hacking by AI agents

Verdict

BLOCK

Grade

Trust score

69 /100

Exposed tools

42 37r · 3w · 2d

Transport

—

License

MIT

Stars

Overview

From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.

A Model Context Protocol (MCP) server that provides Cheat Engine-like capabilities for game hacking through Frida. Enables AI assistants and automation tools to perform memory scanning, value modification, pattern matching, function hooking, and code injection.

Features

Memory Operations (Cheat Engine Style)

Value Scanning: Find values in memory by type (int8-64, float, double, string)
Scan Refinement: Narrow results with scan_next, scan_changed, scan_unchanged
Pattern Scanning: Array of Bytes (AoB) with wildcard support (??)
Memory Read/Write: Read and modify memory with type awareness

Function Hooking & Code Injection

Intercept Functions: Hook with onEnter/onLeave JavaScript callbacks
Replace Functions: Make functions return custom values
Module Hooking: Hook by module!function name
Symbol Resolution: Resolve exports to addresses

Process Management

Process Enumeration: List and filter running processes
Attach/Detach: Connect to running processes
Spawn & Resume: Start processes suspended for early hooking

Debugging

Breakpoints: Software breakpoints via hooks
Register Access: Read CPU registers at breakpoints
Module Analysis: List modules, exports, imports

Window Interaction (Windows)

Screenshot Capture: Take screenshots of game windows
Keyboard Input: Send keystrokes to game windows
Window Management: List, focus, and interact with windows

Installation

# Install from PyPI (coming soon)
pip install frida-game-hacking-mcp

# Or install from source
git clone https://github.com/0xhackerfren/frida-game-hacking-mcp.git
cd frida-game-ha

Read from source at commit 0c827552e306OBSERVED · 2026-10-07

Connect

Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control.

claude-code

claude mcp add frida-game-hacking-mcp -- uvx frida-game-hacking-mcp

claude-desktop

{
  "mcpServers": {
    "frida-game-hacking-mcp": {
      "command": "uvx",
      "args": [
        "frida-game-hacking-mcp"
      ]
    }
  }
}

Exposed tools (42)

37 read · 3 write · 2 destructive. Blast radius: 2 tools can delete or overwrite — an agent that can be talked into calling a tool can be talked into calling this one.

Tool	Risk	Description
`attach`	read
`call_rpc`	read
`check_installation`	read
`clear_scan`	destructive
`detach`	read
`focus_window`	read
`get_documentation`	read
`get_module_exports`	read
`get_module_imports`	read
`get_module_info`	read
`get_scan_results`	read
`get_session_info`	read
`hook_function`	read
`hook_native_function`	read
`intercept_module_function`	read
`list_breakpoints`	read	List all active breakpoints.
`list_capabilities`	read
`list_hooks`	read
`list_memory_regions`	read
`list_modules`	read
`list_processes`	read
`list_windows`	read
`load_script`	read
`read_memory`	read
`read_registers`	read
`remove_breakpoint`	destructive
`replace_function`	read
`resolve_symbol`	read
`resume`	read
`scan_changed`	read
`scan_next`	read
`scan_pattern`	read
`scan_unchanged`	read
`scan_value`	read
`screenshot_screen`	read
`screenshot_window`	read
`send_key_to_window`	write
`set_breakpoint`	write
`spawn`	read
`unhook_function`	read
`unload_script`	read
`write_memory`	write

Trust audit

BLOCKgrade D · trust 69/100 Do not install this without reading the findings. The audit found something that could harm you or your machine.

Layer	What it checks	Result
L0	Provenance & inventory	PASS
L1	Static analysis of the code	PASS
L2	Instruction surface (what it tells the agent)	FAIL
L3	Class-specific surface	WARN
L4	Behavioural (sandbox)	SKIPPED

What the source does

Filesystem: declared (1 observation(s))
Network: none-observed
Shell: none-observed
Dependencies: pinned
Secrets in source: none-found

Findings (11)

HIGHPrompt injection · prompt.override · CWE-94, CWE-1427

examples/custom_script_rpc.md:42

// Set health address for god mode

Why it matters. asks the agent to drop prior instructions or safety

Fix. remove the instruction

HIGHPrompt injection · prompt.override · CWE-94, CWE-1427

examples/custom_script_rpc.md:48

// Toggle god mode

Why it matters. asks the agent to drop prior instructions or safety

Fix. remove the instruction

HIGHPrompt injection · prompt.override · CWE-94, CWE-1427

examples/custom_script_rpc.md:87

# Toggle god mode on

Why it matters. asks the agent to drop prior instructions or safety

Fix. remove the instruction

MEDIUMFilesystem / path · mcp.destructive_tools · CWE-22, CWE-59

clear_scan, remove_breakpoint

Why it matters. 2 tool(s) can delete or overwrite

Fix. prefer a read-only mode or scoped tokens; the page states the blast radius

LOWObfuscation / stealth · obf.decode_call · CWE-506, CWE-94

src/frida_game_hacking_mcp/server.py:614

raw_bytes = bytes.fromhex(response['hex'])

LOWObfuscation / stealth · obf.decode_call · CWE-506, CWE-94

src/frida_game_hacking_mcp/server.py:660

write_bytes = bytes.fromhex(data.replace(" ", ""))

LOWObfuscation / stealth · obf.decode_call · CWE-506, CWE-94

src/frida_game_hacking_mcp/server.py:668

write_bytes = bytes.fromhex(data.replace(" ", ""))

LOWObfuscation / stealth · obf.decode_call · CWE-506, CWE-94

src/frida_game_hacking_mcp/server.py:990

current_value = _unpack_value(bytes.fromhex(c['hex']), value_type)

LOWObfuscation / stealth · obf.decode_call · CWE-506, CWE-94

src/frida_game_hacking_mcp/server.py:1082

current_value = _unpack_value(bytes.fromhex(c['hex']), value_type)

LOWPrompt injection · prompt.override · CWE-94, CWE-1427

examples/custom_script_rpc.md:7

You want to create a reusable "god mode" script that can be toggled on/off.

Why it matters. asks the agent to drop prior instructions or safety

Fix. remove the instruction

LOWPrompt injection · prompt.override · CWE-94, CWE-1427

examples/custom_script_rpc.md:51

return "God mode: " + (godModeEnabled ? "ON" : "OFF");

Why it matters. asks the agent to drop prior instructions or safety

Fix. remove the instruction

Gates applied: instruction_override, no_behavioural_pass.

Audited 2026-10-07 · audit v0.4.1 · source sha 0c827552e306full audit observations/trust-audit/mcp-server/0xhackerfren__frida-game-hacking.json · Report an issue / request a re-scan

Audit history

Every audit this server has had. A grade with a past is a grade somebody is still checking.

Date	Source	Verdict	Grade	Score	Change
2026-10-07	`0c827552e306`	BLOCK	D	69	first audit

Questions

What is the Frida Game Hacking MCP server?

A MCP implementation of Frida that seeks to emulate Cheat Engine functionally to allow for seamless Game Hacking by AI agents

What tools does Frida Game Hacking expose?

42 in total: 37 read-only, 3 that write, and 2 that can delete or overwrite (clear_scan, remove_breakpoint). Every one is listed on this page with its risk.

Is Frida Game Hacking safe to connect to an agent?

No — not without reading the findings first. The audit graded it D (69/100) and found 3 critical or high issues in the source. Each one is listed on this page with the file and line it is on. Separately from the audit: 2 of its tools can destroy data, so scope the token you give it to what you actually need.

What credentials does Frida Game Hacking need?

No credential environment variables were found in its source, so it appears to need none.

How current is this page?

The grade is for one exact copy of the source (0c827552e306), read on 2026-10-07. The repository is watched and re-audited when it changes.

Source	0xhackerfren/frida-game-hacking-mcp
PyPI	`frida-game-hacking-mcp`
License	MIT
Activity	pushed 306d ago