Skip to content
mcp/harbor
LangChain

LLM Sandbox for LangChain

io.github.vndee/llm-sandbox

Securely run LLM-generated code in isolated containers across 7 languages and 3 container backends.

client:LangChain transport:stdio runtime:pypi

Install LLM Sandbox in LangChain

pip install langchain-mcp-adapters 

from langchain_mcp_adapters.client import MultiServerMCPClient

client = MultiServerMCPClient({
        "llm-sandbox": {
            "transport": "stdio",
            "command": "uvx",
            "args": ["llm-sandbox"],
        }
})

tools = await client.get_tools()

get_tools() returns the server's tools as LangChain tools, ready for an agent. LangChain docs

LLM Sandbox in other clients

LLM Sandbox MCP server