Skip to content
mcp/harbor
LangChain

airlock for LangChain

io.github.adamorad/airlock

Local daemon giving AI agents named locks, shared state, events, and a task queue over MCP.

client:LangChain transport:stdio runtime:oci

Install airlock in LangChain

pip install langchain-mcp-adapters 

from langchain_mcp_adapters.client import MultiServerMCPClient

client = MultiServerMCPClient({
        "airlock": {
            "transport": "stdio",
            "command": "docker",
            "args": ["run", "-i", "--rm", "ghcr.io/adamorad/airlock:2.0.0"],
        }
})

tools = await client.get_tools()

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

airlock in other clients

airlock MCP server