Atlas / MCP servers / 1193776794 / Frida

FridaSAFE

mcp/1193776794/frida-4
Verdict
SAFE
Grade
B
Trust score
89 /100
Exposed tools
10 7r · 1w · 2d
Transport
stdio
License
—
Stars
70
01

Overview

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

AI 驱动的 Android 动态分析工具。通过 MCP (Model Context Protocol) 让 AI 直接操控 Frida,实现自动化逆向分析。

AI (Claude) → MCP Server → Frida CLI → zygisk-gadget (手机) → 结果返回

前提条件

  • Python >= 3.10
  • Android 手机已 root,安装 Magisk
  • 安装 zygisk-gadget Magisk 模块(固定端口 14725)
  • ADB 已连接手机

安装

pip install .

安装后运行一键配置(注册 MCP + 安装 Skills):

frida-mcp-setup

或手动配置,在 ~/.claude.json 中添加:

{
"mcpServers": {
"frida-agent": {
"command": "frida-mcp"
}
}
}

MCP Tools

Skills(Claude Code 技能)

安装后可在 Claude Code 中使用:

  • `/reverse-analyze` — 逆向分析与动态 Hook,结合 IDA 静态分析 + Frida 动态验证
  • `/trace-vm` — VM 保护函数分析,指导人工 trace 并由 AI 分析结果

使用示例

基本 Hook 流程

用户: hook 淘宝的 Cipher.doFinal 看看加密参数

AI 自动执行:
1. connect()                    — 建立连接
2. spawn_and_inject(            — 启动并注入
"com.taobao.taobao",
"Java.perform(function() { ... })"
)
3. 提示用户触发操作              — "请点击登录按钮"
4. get_messages()               — 获取 hook 结果
5. 分析并展示加密参数和返回值

结合 IDA 静态分析

用户: /reverse-analyze 分析 libsgmain.so 中 0x1234 处的函数

AI 自动执行:
1. IDA MCP 反编译目标函数,分析参数和返回值类型
2. 生成 Frida Hook 脚本
3. spawn_and_inject 注入
4. 交叉验证静态分析和动态结果

工作原理

本工具使用 Frida CLI 而非 frida-python API,通过 frida -H 127.0.0.1:14725 -F -l script.js -o output.txt 注入脚本:

  • 脚本中的 send() 调用自动转换为 console.log(JSON.stringify())
  • 所有脚本自动包裹 try-catch 防止注入崩溃
  • 输出通过 -o 标志写入文件,get_messages 时停止 frida 进程以刷新文件

项目结构

src/frida_mcp/
├── server.py   
Read from source at commit 58d11a19ffd7OBSERVED · 2026-10-07
Advertisement
02

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-agent-mcp -- uvx frida-agent-mcp
claude-desktop
{
  "mcpServers": {
    "frida-agent-mcp": {
      "command": "uvx",
      "args": [
        "frida-agent-mcp"
      ]
    }
  }
}
03

Exposed tools (10)

7 read · 1 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.

ToolRiskDescription
connectreadConnect to the Frida gadget on the device.
detachreadDetach from the current session and unload any injected scripts.
executewriteInject a Frida JavaScript script into the frontmost application.
get_messagesreadGet messages collected from the injected script
kill_appdestructiveForce stop an Android app by package name.
launch_appreadLaunch an Android app by package name.
list_appsreadList running applications on the connected device.
logcatreadGet Android logcat output. Useful for debugging crashes after script injection.
reconnectreadReconnect to the gadget after an app crash.
spawn_and_injectdestructiveKill app, relaunch, connect, and inject script in one step.
04

Trust audit

SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.

LayerWhat it checksResult
L0Provenance & inventoryPASS
L1Static analysis of the codePASS
L2Instruction surface (what it tells the agent)PASS
L3Class-specific surfaceWARN
L4Behavioural (sandbox)SKIPPED

What the source does

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

Findings (2)

MEDIUMFilesystem / path · mcp.destructive_tools · CWE-22, CWE-59
kill_app, spawn_and_inject
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
LOWInventory / provenance · inv.no_license · CWE-1104
Why it matters. no LICENSE file and no repo licence
Fix. add a licence

Gates applied: no_behavioural_pass, no_license.

Audited 2026-10-07 · audit v0.4.1 · source sha 58d11a19ffd7full audit observations/trust-audit/mcp-server/1193776794__frida-4.json · Report an issue / request a re-scan
05

Audit history

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

DateSourceVerdictGradeScoreChange
2026-10-0758d11a19ffd7SAFEB89first audit
06

Questions

What tools does Frida expose?

10 in total: 7 read-only, 1 that write, and 2 that can delete or overwrite (kill_app, spawn_and_inject). Every one is listed on this page with its risk.

Is Frida safe to connect to an agent?

The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B. 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 need?

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

How does Frida run?

It speaks stdio, so it runs as a local process your client starts. It is published on PyPI as frida-agent-mcp.

How current is this page?

The grade is for one exact copy of the source (58d11a19ffd7), read on 2026-10-07. The repository is watched and re-audited when it changes.

Advertisement