tre for LangChain
com.tre-app/tre
Tre — shared memory kanban for humans and agents (MCP Streamable HTTP).
client:LangChain
transport:streamable-http
Install tre in LangChain
pip install langchain-mcp-adapters
from langchain_mcp_adapters.client import MultiServerMCPClient
client = MultiServerMCPClient({
"tre": {
"transport": "streamable_http",
"url": "https://tre-app.com/api/mcp",
}
})
tools = await client.get_tools()
get_tools() returns the server's tools as LangChain tools, ready for an agent. LangChain docs