Skip to content

LangChain Sequential Thinking sequentialthinking

How to: LangChain Sequential Thinking sequentialthinking

client:LangChain transport:stdio tool:sequentialthinking

Add Sequential Thinking 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({
        "server-sequential-thinking": {
            "transport": "stdio",
            "command": "npx",
            "args": ["-y", "@modelcontextprotocol/server-sequential-thinking"],
        }
})

tools = await client.get_tools()
  1. 02

    Save the file and restart LangChain.

  2. 03

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

  3. 04

    If nothing happens, check the server is running and that Sequential Thinking'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

Same tool, other clients

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.