hot memory mcp for LangChain
io.github.michael-denyer/hot-memory-mcp
Two-tier memory: hot cache (0ms) + semantic search. Self-organizing.
client:LangChain
transport:stdio
runtime:pypi
Install hot memory mcp in LangChain
pip install langchain-mcp-adapters
from langchain_mcp_adapters.client import MultiServerMCPClient
client = MultiServerMCPClient({
"hot-memory-mcp": {
"transport": "stdio",
"command": "uvx",
"args": ["hot-memory-mcp"],
}
})
tools = await client.get_tools()
get_tools() returns the server's tools as LangChain tools, ready for an agent. LangChain docs