Skip to content
LangChain

Sequential Thinking for LangChain

io.github.modelcontextprotocol/server-sequential-thinking

Reference server that gives a model a structured scratchpad for step-by-step problem solving, with revision and branching of earlier thoughts.

client:LangChain transport:stdio runtime:npm tools:1

Install Sequential Thinking in LangChain

pip install langchain-mcp-adapters

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()

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

What LangChain can do once it is connected

Sequential Thinking in other clients