Skip to content
mcp/harbor
LangChain

runeward for LangChain

io.github.runewardd/runeward

Governed execution cells for AI agents: Docker/K8s sandboxes with policy, audit, and approvals.

client:LangChain transport:stdio runtime:oci

Install runeward in LangChain

pip install langchain-mcp-adapters 

from langchain_mcp_adapters.client import MultiServerMCPClient

client = MultiServerMCPClient({
        "runeward": {
            "transport": "stdio",
            "command": "docker",
            "args": ["run", "-i", "--rm", "ghcr.io/runewardd/runeward:v0.1.4"],
        }
})

tools = await client.get_tools()

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

runeward in other clients

runeward MCP server