Zum Hauptinhalt springen
tsecurity.de LIVE
Echtzeit-Radar & Feeds
Alle RSS Feeds
👥 Community & Social
IT Security Toolsboha v0.20.2(20.09.2026 um 16:32 Uhr)
IT Security Toolscyberbro v0.15.0(20.09.2026 um 17:32 Uhr)
IT Security NachrichtenUS, China seek Xi-Trump summit deliverables in New York talks(20.09.2026 um 16:34 Uhr)
Sicherheitslücken (CVE)Gyazo Server Vulnerability Targeted to Steal Millions of User Records(20.09.2026 um 17:02 Uhr)
IT Security NachrichtenHearth and Hamlet Review (PC)(20.09.2026 um 16:40 Uhr)
IT Security NachrichtenKI knackt Weltkriegs-Funkspruch - Historiker irrten sich 108 Jahre lang(20.09.2026 um 16:41 Uhr)
IT Security Toolsboha v0.20.2(20.09.2026 um 16:32 Uhr)
IT Security Toolscyberbro v0.15.0(20.09.2026 um 17:32 Uhr)
IT Security NachrichtenUS, China seek Xi-Trump summit deliverables in New York talks(20.09.2026 um 16:34 Uhr)
Sicherheitslücken (CVE)Gyazo Server Vulnerability Targeted to Steal Millions of User Records(20.09.2026 um 17:02 Uhr)
IT Security NachrichtenHearth and Hamlet Review (PC)(20.09.2026 um 16:40 Uhr)
IT Security NachrichtenKI knackt Weltkriegs-Funkspruch - Historiker irrten sich 108 Jahre lang(20.09.2026 um 16:41 Uhr)
Intelligence View
⚡ tsecurity.de Intelligence

I Gave My AI Full Control of My Laptop — Here's What Happened 🤖💻

Reagiere als Erste:r — dein Feedback zählt!

The Moment I Realized AI Was Stuck in a Text Box
Picture this: You're deep in a coding session. Your AI buddy just gave you the perfect shell command. You copy it. You paste it. You run it. You go back. You paste the output. The AI says "try this instead." You copy. You paste. You run. You go back...
Over and over and over.
I snapped one day and thought: "Why can't the AI just... DO it?"

So I built a thing. And it changed everything.

🔗 MCP Server Git Hub Link

🎬 Let Me Show You What It Looks Like

Instead of the old copy-paste dance, my conversations now go like this:

Me: "What's eating all my RAM right now?"

AI: Actually checks my running processes and responds: "Chrome is using 2.1GB across 47 processes 😅. VS Code is at 890MB. Want me to kill any of these?"

Me: "Nah, but can you find all those .tmp files in my Downloads and clean them up?"

AI: Searches my filesystem, finds 23 temp files, and asks: "Found 23 .tmp files taking up 340MB. Here's the list. Want me to delete them?"

Me: "Do it."

AI: Actually deletes them. "Done! Freed up 340MB. 🎉"

That's real. That's not a mockup. That's my actual workflow now.

🧩 "But HOW?" — Enter MCP

MCP (Model Context Protocol) is like a USB-C port for AI. It's an open standard that lets AI models plug into external tools through a clean, standardized interface.

You, talking to AI         The Magic Bridge           Your Computer
┌─────────────────┐      ┌──────────────┐      ┌──────────────────┐
│ "Delete those   │ ───► │   MCP Server │ ───► │ *actually deletes │
│  temp files"    │      │  (my project)│      │  the files*       │
│                 │ ◄─── │              │ ◄─── │                  │
│ "Done! 340MB    │      │              │      │                  │
│  freed up 🎉"  │      └──────────────┘      └──────────────────┘
└─────────────────┘

The beautiful part? One server works with multiple AI clients — Google Antigravity, Claude Code, Claude Desktop. Build once, use everywhere.

🧰 28+ Tools. Yes, Really.

I went a little overboard. Here's the full arsenal:

💻 System Tools — "Be my sysadmin"

  • 🖥️ "What's my CPU at?" → Returns real-time CPU, memory, and disk stats
  • "Run git status" → Executes PowerShell commands (with safety confirmation!)
  • 📊 "What's hogging my memory?" → Lists processes sorted by RAM/CPU usage
  • 💀 "Kill process 4521" → Terminates it (after asking you first 👀)
  • 🔋 "Am I plugged in?" → Battery level + charging status
  • 🌐 "Show me my IP address" → Full network interface breakdown

📁 File Management — "Be my file explorer"

  • 📂 "What's in my Documents folder?" → Lists files and directories
  • 📄 "Read config.json" → Displays file contents
  • "Create a 'Projects' folder" → Makes directories (recursive!)
  • 🔍 "Find all .py files" → Glob-based file search
  • ↗️ "Move report.pdf to Archive" → Renames or moves files
  • 🗑️ "Delete old-backup/" → Removes files/dirs (with confirmation)

🌐 Web Tools — "Be my browser"

  • 🔎 "Google Python best practices" → Searches via DuckDuckGo
  • 📰 "Grab the text from this URL" → Fetches + extracts clean text
  • ⬇️ "Download this file" → Saves files from any URL

📦 App Management — "Be my IT department"

  • 📋 "What do I have installed?" → Lists all apps (via winget)
  • 📥 "Install Firefox" → Installs from winget repository
  • 🔄 "Update all my apps" → Updates installed applications

🔧 Utilities — "Be my Swiss Army knife"

  • 📎 "What's on my clipboard?" → Reads clipboard contents
  • ✏️ "Copy this to clipboard" → Sets clipboard text
  • 📸 "Take a screenshot" → Captures your screen

🔐 "Wait... Isn't This Terrifying?"

You're thinking it. I thought it too.

"You gave an AI the power to delete files and kill processes?!"

Yes. But. I'm not a maniac. Let me introduce you to my favorite feature:

The Two-Phase Confirmation System 🫡

Every dangerous operation follows a strict handshake:

You: "Delete that folder"

AI ──► MCP Server: "I want to delete /Users/me/old-stuff"
MCP Server: "Here's a token: abc-123. Show this warning to the user."

AI ──► You: "⚠️ I'm about to delete /Users/me/old-stuff. 
        This can't be undone. OK?"

You: "Yes, do it."

AI ──► MCP Server: "confirm_action(token='abc-123')"
MCP Server: *actually deletes it*
AI ──► You: "Done! ✅"

No token = no execution. Period.

And the token? It expires in 5 minutes. So a sneaky prompt injection can't stash a delete command and run it later.

The Security Wall 🧱

Even with confirmation, the server blocks genuinely dangerous stuff:

  • 🚫 Can't touch system filesC:\Windows\System32? Nope.
  • 🚫 Can't probe your networklocalhost, 192.168.x.x, cloud metadata endpoints? All blocked.
  • 🚫 Can't write executables — Trying to create .exe, .bat, .ps1 files? Denied.
  • 🚫 Can't open shady programs — Only whitelisted apps (notepad, chrome, etc.) work.

I wrote 39 security tests covering every attack vector I could think of. 39/39 pass.

⚡ Set It Up in 5 Minutes

For real. Five minutes. Here we go:

1. Clone + Install

git clone https://github.com/ViswaSrimaan/mcp_servers.git
cd mcp_servers
python -m venv .venv
.venv\Scripts\activate
pip install mcp psutil httpx beautifulsoup4 pyperclip Pillow duckduckgo-search

2. Pick Your AI Client

🟢 Google Antigravity

Edit %USERPROFILE%\.gemini\antigravity\mcp_config.json:

{
  "mcpServers": {
    "laptop-assistant": {
      "type": "stdio",
      "command": "C:\\your\\path\\mcp_servers\\.venv\\Scripts\\python.exe",
      "args": ["C:\\your\\path\\mcp_servers\\server.py"]
    }
  }
}

Restart Antigravity. Done. ✅

🟣 Claude Code (VS Code)

Create .mcp.json in your workspace root:

{
  "mcpServers": {
    "laptop-assistant": {
      "type": "stdio",
      "command": "C:\\your\\path\\mcp_servers\\.venv\\Scripts\\python.exe",
      "args": ["C:\\your\\path\\mcp_servers\\server.py"]
    }
  }
}

Reload VS Code. Done. ✅

🔵 Claude Desktop

Edit %APPDATA%\Claude\claude_desktop_config.json:

{
  "mcpServers": {
    "laptop-assistant": {
      "command": "C:\\your\\path\\mcp_servers\\.venv\\Scripts\\python.exe",
      "args": ["C:\\your\\path\\mcp_servers\\server.py"]
    }
  }
}

Restart Claude Desktop. Done. ✅

3. Start Chatting 🎉

Ask your AI to check your battery, list your files, or search the web. It just... works.

🏗️ Under the Hood (For the Curious)

The architecture is dead simple and very extensible:

server.py                 ← Entry point, registers everything
├── src/safety.py         ← Token-based confirmation system
├── src/security_config.py← All the security rules
└── src/tools/
    ├── system_tools.py   ← 7 tools (CPU, processes, battery...)
    ├── file_tools.py     ← 9 tools (read, write, search...)
    ├── web_tools.py      ← 3 tools (search, fetch, download)
    ├── app_tools.py      ← 5 tools (install, update, uninstall)
    └── utility_tools.py  ← 4 tools (clipboard, screenshot)

Want to add a tool? It's literally this:

@mcp.tool()
def vibe_check() -> str:
    """Check the vibes of your system.

    Returns a vibe report based on CPU temp and battery level.
    """
    # your code here
    return json.dumps({"vibes": "immaculate"})

Register it, restart, and your AI can use it immediately. That's the power of MCP.

🔮 What's Coming Next

This is just v1. Here's my roadmap:

  • 🐧 Linux and macOS support — Windows-only no more
  • 🤖 Task automation — chain tools into multi-step workflows
  • 🔌 Plugin system — drop in custom tool modules
  • 🌐 Browser automation — full web interaction, not just fetching

🫵 Your Turn

I built this to scratch my own itch — I wanted my AI to stop being a talker and start being a doer. If that resonates with you, give it a try:

github.com/ViswaSrimaan/mcp_servers

Star it, fork it, break it, fix it, PR it. The whole repo is MIT licensed and contributions are very welcome.

Got questions? Found a bug? Want to show off what you built with it? Drop a comment below — I read every one! 💬

Ähnliche Beiträge
🔍 Verwandte News

Auch interessante Nachrichten I Gave My AI Full Control of My Laptop — Here's What Happened 🤖💻

Thematisch verwandte Begriffe: Gave, Full, Control, Laptop · 6 Treffer

Laden...

Videos werden geladen ...

Laden...

Beiträge werden geladen ...

Laden...

Videos werden geladen ...

Laden...

Beiträge werden geladen ...

Laden...

Videos werden geladen ...

Laden...

Beiträge werden geladen ...

Laden...

Videos werden geladen ...

Laden...

Beiträge werden geladen ...

Laden...

Videos werden geladen ...

Zum Aktualisieren ziehen
ZERO-DAY CVE-2026-93956 | A flaw has been found in olivier-ls PHP-FTS up to 1.1.2. Affected by thi…
Advisory →
TTS Reader • tsecurity.de Voice
tsecurity.de Icon
tsecurity.de App
Offline-Lesen, Eilmeldungen & 0ms Ladezeit

Installiere tsecurity.de direkt auf deinen Home-Bildschirm für das ultimative Vollbild-Magazinerlebnis ohne Browser-Leisten.

Nächster Beitrag
Themen-Radar & Intelligence Matrix
Echtzeit-Taxonomie nach Angriffsvektoren & Plattformen
Community Radar & Live Chat
Sentinel Bot online • Live-Stream
Dein Cluster: Security Explorer
Match:
lädt…
Verbindung zum Community-Stream wird aufgebaut...
Bearbeitungsmodus — Senden überschreibt deine Nachricht
Community-Puls — was gerade passiert
lädt…
Aktivitäten deiner Analysten
lädt…
Neues Thema oder Eilmeldung einreichen

Reiche interessante Links, Zero-Days oder Debatten ein. Die Community entscheidet per Upvote über die Veröffentlichung.

Heiß diskutierte Einreichungen
🔖 Gespeicherte Artikel
📂 Keine gespeicherten Artikel vorhanden.
Zurück Ziehen Vor
Links: vorheriger Artikel Rechts: nächster Artikel unten: schließen
News NIS-2 Frühwarnung Tier-1 Intel ⏱️ 3 Min vor 10 Min
Artikeldaten werden geladen...

Zurück: vorheriger Vor: nächster
↗ Original-Quelle
Social Reaktionen Deine Reaktion zählt
Einstufung & Relevanz-Poll 0 Stimmen
In sozialen Netzwerken teilen 1-Klick