Destructive Command Interceptor Connector for AI agents.
3 live capabilities
Protect your terminal from dangerous bash commands
Waiting for input…
Why people use Destructive Command Interceptor
Stop terminal disasters with Destructive Command Interceptor bash security
With this MCP, that anxiety disappears. The interceptor sits between the agent and the shell, doing the scanning for you. It catches the mistakes and the hidden attacks in milliseconds, letting you focus on the actual work instead of babysitting a terminal prompt.
What Vinkius changes
That it adds a deterministic security layer to your terminal-based AI workflows.
Use it from Claude, ChatGPT, Cursor or another AI client you already have.
One account · 6,100+ Connectors
- Real-world use case 01
Preventing accidental root deletions
An agent tries to clean up a directory but accidentally targets the root path.
- Real-world use case 02
Blocking malicious curl-to-shell pipes
A user asks an agent to run a script from a URL.
- Real-world use case 03
Detecting encoded payload attacks
A malicious prompt attempts to hide a destructive command using Base64.
Complete set · 3capabilities
The complete Destructive Command Interceptor capability set.
These are the exact actions your AI can choose when you ask it to work with Destructive Command Interceptor.
01—03
3 capabilities in this set.
Part of 3 available through Destructive Command Interceptor.
- 01 Capability
Check pipe security
Inspects command chains to find risky pipes that could lead to unintended execution. It prevents dangerous data flows into shell interpreters.
- 02 Capability
Get blocked pattern info
Explains exactly why a specific command was flagged. It helps you understand the security logic behind a blocked action.
- 03 Capability
Intercept command
Evaluates raw command strings to see if they match any dangerous patterns. It's the primary gatekeeper for all incoming shell requests.
Set up in minutes
One URL. Then ask Destructive Command Interceptor to work.
Claude and ChatGPT only need the Connector URL. Copy it once, add it in settings, and use Destructive Command Interceptor from the conversation.
Choose your client
Live previewAdvanced clients IDE · CLI
Claude · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_xxoJzaOinEubeTXHguCmBfyt34pYTbvuilcXOTYh/mcp - Step 01
Open Connectors
In Claude Web or Claude Desktop, open Settings and choose Connectors.
- Step 02
Add the URL
Choose Add custom connector, name it Destructive Command Interceptor, and paste the URL above.
- Step 03
Turn it on in chat
Select +, open Connectors, and enable Destructive Command Interceptor for the conversation.
ChatGPT · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_xxoJzaOinEubeTXHguCmBfyt34pYTbvuilcXOTYh/mcp - Step 01
Open MCP settings
On desktop, open Settings and MCP servers. On web, open your workspace app or connector settings.
- Step 02
Add the URL
Choose Add server with Streamable HTTP, or create a custom MCP app, then paste the Destructive Command Interceptor URL.
- Step 03
Save and start
Save the connection and enable Destructive Command Interceptor in your conversation. Desktop may ask you to restart once.
Cursor · IDE configuration
Advanced setup
{
"mcpServers": {
"destructive-command-interceptor": {
"url": "https://edge.vinkius.com/vk_preview_xxoJzaOinEubeTXHguCmBfyt34pYTbvuilcXOTYh/mcp"
}
}
}- Step 01
Open MCP Settings
Press Cmd+Shift+P (macOS) or Ctrl+Shift+P (Windows/Linux) → search "MCP Settings"
- Step 02
Add the server config
Paste the JSON configuration above into the mcp.json file that opens
- Step 03
Save the file
Cursor will automatically detect the new Connector
- Step 04
Start using Destructive Command Interceptor
Open Agent mode in chat and ask: "Using Destructive Command Interceptor, help me...". 3 tools available
VS Code Copilot · IDE configuration
Advanced setup
{
"mcpServers": {
"destructive-command-interceptor": {
"url": "https://edge.vinkius.com/vk_preview_xxoJzaOinEubeTXHguCmBfyt34pYTbvuilcXOTYh/mcp"
}
}
}- Step 01
Create MCP config
Create a .vscode/mcp.json file in your project root
- Step 02
Add the server config
Paste the JSON configuration above
- Step 03
Enable Agent mode
Open GitHub Copilot Chat and switch to Agent mode using the dropdown
- Step 04
Start using Destructive Command Interceptor
Ask Copilot: "Using Destructive Command Interceptor, help me...". 3 tools available
Windsurf · IDE configuration
Advanced setup
{
"mcpServers": {
"destructive-command-interceptor": {
"url": "https://edge.vinkius.com/vk_preview_xxoJzaOinEubeTXHguCmBfyt34pYTbvuilcXOTYh/mcp"
}
}
}- Step 01
Open MCP Settings
Go to Settings → MCP Configuration or press Cmd+Shift+P and search "MCP"
- Step 02
Add the server
Paste the JSON configuration above into mcp_config.json
- Step 03
Save and reload
Windsurf will detect the new server automatically
- Step 04
Start using Destructive Command Interceptor
Open Cascade and ask: "Using Destructive Command Interceptor, help me...". 3 tools available
Cline · IDE configuration
Advanced setup
{
"mcpServers": {
"destructive-command-interceptor": {
"url": "https://edge.vinkius.com/vk_preview_xxoJzaOinEubeTXHguCmBfyt34pYTbvuilcXOTYh/mcp"
}
}
}- Step 01
Open Cline MCP Settings
Click the Connectors icon in the Cline sidebar panel
- Step 02
Add remote server
Click "Add Connector" and paste the configuration above
- Step 03
Enable the server
Toggle the server switch to ON
- Step 04
Start using Destructive Command Interceptor
Ask Cline: "Using Destructive Command Interceptor, help me...". 3 tools available
Claude Code · Terminal command
Advanced setup
claude mcp add destructive-command-interceptor --transport http "https://edge.vinkius.com/vk_preview_xxoJzaOinEubeTXHguCmBfyt34pYTbvuilcXOTYh/mcp"- Step 01
Install Claude Code
Run npm install -g @anthropic-ai/claude-code if not already installed
- Step 02
Add the Connector
Run the command above in your terminal
- Step 03
Verify the connection
Run claude mcp to list connected servers, or type /mcp inside a session
- Step 04
Start using Destructive Command Interceptor
Ask Claude: "Using Destructive Command Interceptor, show me...". 3 tools are ready
Where the request belongs
Work Destructive Command Interceptor can move forward.
This is for anyone giving an AI agent access to a terminal and needing to prevent catastrophic system errors or security breaches.
DevOps Engineer
Automating infrastructure tasks via agents while ensuring a single typo doesn't take down a production environment.
Security Researcher
Testing shell scripts and command patterns in a controlled, monitored way.
Software Developer
Using Cursor or Windsurf to manage local files and build projects without worrying about accidental mass deletions.
Build the capability set
Add more capabilities.
Each Connector adds new actions and data without changing how you work.
Browse ConnectorsDoppler
Manage secrets and environment variables via Doppler. list projects, audit secrets, and track activity logs from any AI agent.
PiLAB
Manage infrastructure and security via PiLAB. control PiVirt virtual machines, inspect PiTrust certificates, and oversee 3SO OAuth clients directly from any AI agent.
OOPSpam
Block spam submissions on your forms and comments with an AI-powered filter that catches bots without annoying real users.
Bcrypt Hash Engine
Hash and verify passwords with the industry-standard bcrypt algorithm. Two capabilities in one: hash with configurable salt rounds, and verify against stored hashes. Pure JS. zero compilation.
X Ads (Twitter)
Connect your X Ads account to any AI agent. audit campaigns, analyze line item performance, and pull engagement reports through natural conversation.
Box
Store, share, and collaborate on files securely with enterprise-grade cloud content management and governance controls.
Bring your own AI
Change the model, client or framework. Keep Destructive Command Interceptor connected.
-
Claude -
ChatGPT -
Gemini -
Cursor -
VS Code -
Windsurf -
ZCode -
Cline -
Zed -
Continue -
Kiro -
Roo Code -
Zencoder -
Goose -
Void -
Augment Code -
Amp -
Qodo -
Tabnine -
Pieces -
Sourcegraph Cody -
JetBrains -
Warp -
Amazon Q -
Antigravity -
BoltAI -
Raycast -
Jan -
LM Studio -
AnythingLLM -
Open WebUI -
Msty -
Cherry Studio -
LibreChat -
TypingMind -
Chorus -
5ire -
n8n -
LangChain -
LlamaIndex -
CrewAI -
Vercel AI SDK
Before you connect
Questions about Destructive Command Interceptor.
The practical details behind the request, access and result.
How does Destructive Command Interceptor protect my terminal?
It acts as a security gate that inspects every command before it executes. It looks for dangerous patterns, hidden encoding, and risky pipes to stop harmful actions in their tracks.
Can this MCP stop an AI agent from deleting my files?
Yes. It specifically identifies and blocks destructive patterns like mass deletions or commands targeting sensitive system directories.
Does Destructive Command Interceptor work with any AI client?
Yes, it works with any MCP-compatible client like Claude, Cursor, or Windsurf. Once connected, your agent can use it to validate commands.
Will this slow down my terminal commands?
No. The inspection happens via fast pattern matching and regex, so the delay is negligible compared to the time it takes to actually run a command.
How does it detect hidden or obfuscated commands?
It includes specialized detection for Hex and Base64 encoding, allowing it to see through attempts to hide malicious intent within a command string.
What happens if a command is blocked?
The command is stopped before it ever reaches your shell. Your agent will receive a notification that the action was blocked for security reasons.
How does the interceptor detect hidden commands?
The capability decodes Hex and Base64 encoded strings and checks for variable expansion to reveal the true intent of the command.
Can I check if a pipe is dangerous?
Yes, you can use the check_pipe_security capability to identify if a command is piping data into a shell interpreter like sh or bash.
One connection away
Give your agent a direct line to Destructive Command Interceptor.
Connect Destructive Command Interceptor once. Keep it beside 6,100+ managed Connectors when the next task needs more.
Explore every Connector No credit card required · Free tier available