Budgethelm for LangChain
io.github.xxblv81/budgethelm
See AI agent token spend per project and model, and stop agents that loop or burn tokens.
client:LangChain
transport:streamable-http
Install Budgethelm in LangChain
pip install langchain-mcp-adapters
from langchain_mcp_adapters.client import MultiServerMCPClient
client = MultiServerMCPClient({
"budgethelm": {
"transport": "streamable_http",
"url": "https://agentops.agentops.workers.dev/api/mcp",
}
})
tools = await client.get_tools()
get_tools() returns the server's tools as LangChain tools, ready for an agent. LangChain docs