Token Diet for LangChain
com.clawhard/tokendiet
Count tokens exactly for any text and see if it fits a 128K, 200K or 1M context window.
client:LangChain
transport:streamable-http
tools:1
Install Token Diet in LangChain
pip install langchain-mcp-adapters
from langchain_mcp_adapters.client import MultiServerMCPClient
client = MultiServerMCPClient({
"tokendiet": {
"transport": "streamable_http",
"url": "https://tokendiet.clawhard.com/mcp",
}
})
tools = await client.get_tools()
get_tools() returns the server's tools as LangChain tools, ready for an agent. LangChain docs