Skip to content
mcp/harbor
LangChain

token optimizer for LangChain

io.github.omkar9854/token_optimizer

Reversible context compression for AI agents: cut token usage up to 94%, originals retrievable

client:LangChain transport:stdio runtime:pypi

Install token optimizer in LangChain

pip install langchain-mcp-adapters 

from langchain_mcp_adapters.client import MultiServerMCPClient

client = MultiServerMCPClient({
        "token_optimizer": {
            "transport": "stdio",
            "command": "uvx",
            "args": ["slimctx"],
        }
})

tools = await client.get_tools()

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

token optimizer in other clients

token optimizer MCP server