Creates and manages disposable Docker sandboxes for isolated command execution, with TTL-based cleanup, memory limits, and optional network isolation.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@agent-jail-mcp run 'python3 main.py' in a disposable docker sandbox"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Give your AI agent a jail, not your machine.
Live Demo · Pricing · API Docs
Agent Jail provides disposable, isolated Docker sandboxes for AI agents. Instead of letting agents run commands directly on your machine, Agent Jail creates ephemeral containers where agents can safely execute code.
Perfect for:
🤖 AI code execution (ChatGPT, Claude, etc.)
🧪 Testing untrusted code safely
🔬 Research environments
📚 Educational platforms
🏗️ CI/CD pipelines
Related MCP server: anvil
✅ Disposable sandboxes — auto-cleanup after TTL
✅ Docker isolation — true containerization
✅ Resource limits — RAM/CPU caps per tier
✅ Network isolation — optional per sandbox
✅ TTL-based cleanup — automatic expiration
🔐 Self-serve auth — email/password signup (no API key needed initially)
💎 3 tiers — Free / Pro / Enterprise with enforced quotas
💰 Crypto billing — pay with USDT/TON/BTC via NOWPayments
⚡ Auto-upgrade — webhook → instant tier activation
📊 Usage tracking — full audit log per user
🖥️ Web dashboard — manage sandboxes visually
🔌 REST API — full programmatic control
🤖 Telegram bot — bilingual (FA/EN) glass-button UI
🔧 MCP server — for AI clients (Claude Desktop, etc.)
git clone https://github.com/idiscoord13-sketch/agent-jail-mcp.git
cd agent-jail-mcp
python3 -m venv .venv
source .venv/bin/activate
pip install -r requirements.txtThis server cannot be deployed
Hosting for AI agents: your AI client deploys Docker apps to live HTTPS URLs over MCP.
OCR, transcription, file extraction, and image generation for AI agents via MCP.
MCP server for Superserve sandboxes: create, exec, and manage Firecracker microVMs
Nifty's MCP server — exposes tasks, projects, messages, and files as tools for AI agents.
