LangChain

Connect StackOne MCP to LangChain using the MCP adapters package.

​

Overview

LangChain provides MCP integration through langchain-mcp-adapters, converting MCP tools into LangChain-compatible tools.

Official Docs

​

Installation

uv add langchain langchain-mcp-adapters langchain-openai

​

Quick start

Connect to StackOne MCP and use tools in LangChain:

import os
import asyncio
import base64
from langchain_mcp_adapters.client import MultiServerMCPClient
from langchain.agents import AgentExecutor, create_tool_calling_agent
from langchain_openai import ChatOpenAI
from langchain.prompts import ChatPromptTemplate

# Configure StackOne account
STACKONE_ACCOUNT_ID = "<account_id>"  # Your StackOne account ID

# Encode API key for Basic auth
auth_token = base64.b64encode(
    f"{os.getenv('STACKONE_API_KEY')}:".encode()
).decode()

async def main():
    # Connect to StackOne MCP server
    mcp_client = MultiServerMCPClient({
        "stackone": {
            "url": "https://api.stackone.com/mcp",
            "transport": "streamable_http",
            "headers": {
                "Authorization": f"Basic {auth_token}",
                "x-account-id": STACKONE_ACCOUNT_ID,
                "Content-Type": "application/json",
                "Accept": "application/json,text/event-stream",  # Required by MCP spec
                "MCP-Protocol-Version": "2025-06-18"
            }
        }
    })

    # Get StackOne tools
    tools = await mcp_client.get_tools()

    # Create agent with StackOne tools
llm = ChatOpenAI(model="gpt-5")
    prompt = ChatPromptTemplate.from_messages([
        ("system", "You are a helpful assistant with access to data from connected platforms."),
        ("human", "{input}"),
        ("placeholder", "{agent_scratchpad}")
    ])

    agent = create_tool_calling_agent(llm, tools, prompt)
    agent_executor = AgentExecutor(agent=agent, tools=tools)

    # Run agent
    result = agent_executor.invoke({"input": "List Salesforce accounts"})
    print(result["output"])

asyncio.run(main())

​

Environment variables

STACKONE_API_KEY=<stackone_api_key>
OPENAI_API_KEY=your_openai_key

​

Resources

• LangChain MCP Adapters
• LangChain Documentation
• StackOne Authentication

​

Optimize and secure

With your agent connected, use StackOne’s platform features to optimize performance and secure every call.

Advanced Tool Search

Reduce context and save tokens.

Deep Query

Search synced records for a fraction of the tokens.

Defender

Block prompt injections before they reach your agent.