Skip to content
mcp/harbor
LangChain

context keeper for LangChain

io.github.jarmstrong158/context-keeper

Durable project-memory MCP: decisions, constraints, and pipelines across Claude sessions.

client:LangChain transport:stdio runtime:pypi

Install context keeper in LangChain

pip install langchain-mcp-adapters 

from langchain_mcp_adapters.client import MultiServerMCPClient

client = MultiServerMCPClient({
        "context-keeper": {
            "transport": "stdio",
            "command": "uvx",
            "args": ["context-keeper-mcp"],
        }
})

tools = await client.get_tools()

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

context keeper in other clients

context keeper MCP server