Skip to content

LangChain litmus check_server

How to: LangChain litmus check_server

client:LangChain transport:streamable-http tool:check_server

Add litmus to LangChain

  1. 01

    Open pip install langchain-mcp-adapters and merge this in. Keep any servers already there.

from langchain_mcp_adapters.client import MultiServerMCPClient

client = MultiServerMCPClient({
        "litmus": {
            "transport": "streamable_http",
            "url": "https://polygraph.so/api/mcp",
        }
})

tools = await client.get_tools()
  1. 02

    Save the file and restart LangChain.

  2. 03

    Ask for something check_server does. LangChain lists the server's tools on connect and calls check_server itself — you do not invoke it by name.

  3. 04

    If nothing happens, check the server is running and that litmus's identifier in your config matches the one above exactly.

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

Set these first

litmus will not start until these are set, so check_server never becomes available.

  • POLYGRAPH_API_URL
  • NEXT_PUBLIC_POLYGRAPH_NETWORK

Same tool, other clients

This list was read from the server itself, by connecting to it and calling tools/list on 24 September 2026. It is what the server actually exposes, not what its listing claims.

Mutating and Read-only are read off each tool's name, not its schema — a hint, not a guarantee. The registry stores tool names only; connect the server for its live schemas.