Kiln-AI/Kilntainers
MCP server to give every agent an ephemeral Linux sandboxes for executing shell commands.
This project creates secure, isolated environments where your AI agents can safely run Linux commands. It takes your agent's requests for shell commands and executes them in a temporary, dedicated sandbox, returning the results. This is ideal for developers who are building or managing AI agents that need to interact with a Linux terminal without compromising host system security or stability.
Used by 1 other package. Available on PyPI.
Use this if you need to give multiple LLM agents the ability to execute shell commands like `grep` or `jq` in parallel, without worrying about them interfering with each other or your main system.
Not ideal if your AI agents do not require executing shell commands or if you need persistent storage and state across multiple agent sessions.
Stars
34
Forks
4
Language
Python
License
MIT
Category
Last pushed
Mar 03, 2026
Commits (30d)
0
Dependencies
3
Reverse dependents
1
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/mcp/Kiln-AI/Kilntainers"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
gradion-ai/ipybox
Python code execution sandbox with programmatic MCP tool calling (PTC)
BlackSnufkin/LitterBox
A secure sandbox environment for malware developers and red teamers to test payloads against...
universal-tool-calling-protocol/code-mode
🔌 Plug-and-play library to enable agents to call MCP and UTCP tools via code execution.
buremba/1mcp
Let your agent write code and execute code directly in the browser with WASM
JohanLi233/mcp-sandbox
Python sandboxes for llms