ContextLattice for LangChain
io.github.sheawinkler/contextlattice
Private-by-default, local-first memory/context/task orchestrator for MCP apps and agents.
client:LangChain
transport:streamable-http
Install ContextLattice in LangChain
pip install langchain-mcp-adapters
from langchain_mcp_adapters.client import MultiServerMCPClient
client = MultiServerMCPClient({
"contextlattice": {
"transport": "streamable_http",
"url": "https://contextlattice.io/mcp",
}
})
tools = await client.get_tools()
get_tools() returns the server's tools as LangChain tools, ready for an agent. LangChain docs