Budgetary: estimate token spend for LangChain
io.github.thriftell/budgetary
Pre-flight token-spend estimate (range, scenario, confidence) for a coding task, or an abstention.
client:LangChain
transport:stdio
runtime:npm
Install Budgetary: estimate token spend in LangChain
pip install langchain-mcp-adapters
from langchain_mcp_adapters.client import MultiServerMCPClient
client = MultiServerMCPClient({
"budgetary": {
"transport": "stdio",
"command": "npx",
"args": ["-y", "@budgetary/mcp"],
}
})
tools = await client.get_tools()
get_tools() returns the server's tools as LangChain tools, ready for an agent. LangChain docs