Haldir for LangChain
io.github.exposureguard/haldir
Guardian layer for AI agents: identity, secrets, audit via MCP.
client:LangChain
transport:stdio
runtime:pypi
Install Haldir in LangChain
pip install langchain-mcp-adapters
from langchain_mcp_adapters.client import MultiServerMCPClient
client = MultiServerMCPClient({
"haldir": {
"transport": "stdio",
"command": "uvx",
"args": ["haldir"],
}
})
tools = await client.get_tools()
get_tools() returns the server's tools as LangChain tools, ready for an agent. LangChain docs