LangChain and LangGraph

1. 1

   Load the tools and give them to any agent.

   PythonCopy

   from langchain_mcp_adapters.client import MultiServerMCPClient
   import os
   
   client = MultiServerMCPClient({
       "zomler": {
           "transport": "streamable_http",
           "url": "https://api.zomler.com/mcp",
           "headers": {"Authorization": f"Bearer {os.environ['ZOMLER_API_KEY']}"},
       }
   })
   tools = await client.get_tools()

One tool per platform, plus capabilities and check_balance, at https://api.zomler.com/mcp. Every answer is the envelope: what was measured, when, what was left out and why, and what it cost. Fresh fetches spend credits; anything already held is free.

Keys are created under API keys in the dashboard, where each one's calls and spend are listed. Revoking a key stops this client on its next call. The same key also calls the REST API.

All clients