How to Use the SmartChatAI MCP in LangChain

Q: If I use SmartChatAI with LangChain, can I check the API status?

Absolutely. You can reliably call checkapihealth at the start of your chain to verify connectivity before attempting any complex operations, preventing runtime failures.

Q: How does SmartChatAI handle different types of data when used with LangChain?

It handles three main types: raw text via addtexttoknowledgebase, structured PDFs using addpdftoknowledgebase, and URLs through addwebsitetoknowledgebase.

Build complex reasoning chains with LangChain and the SmartChatAI MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect SmartChatAI MCP to LangChain

Create your Vinkius account to connect SmartChatAI to LangChain — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup SmartChatAI with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Multi-Step Bot Orchestration

Need to build a chain that does more than just talk? You can initiate a process by calling `list_ai_chatbots` to get all available bot IDs. The output of this list becomes the input for your next step, perhaps fetching specific details using `get_chatbot_details`. This lets you string together complex actions where one tool's result dictates the next. This sequential logic is perfect for ReAct agents. You don't just run a single API call; your agent decides to first gather context with `scrape_domain_links`, then use that data in a message via `message_ai_chatbot`, and finally, save the outcome using an external function.

Knowledge Base Data Pipeline

You can feed diverse data into your reasoning chain. Start by training on a website URL with `add_website_to_knowledge_base`. Later, if you get new documents, you'll use `add_pdf_to_knowledge_base` to keep the knowledge base current. The LangChain agent uses these structured tools to ensure its reasoning is always grounded. It treats the content generated by the MCP Server as a verifiable source of truth when answering complex queries.

User Context Management

An agent needs context about who it's talking to. Use `get_authenticated_user_profile` at the start of your chain to fetch user details and personalize responses. You can then check past interactions by calling `get_bot_chat_history`, which provides a clean transcript you can feed back into the prompt. This makes the entire workflow stateful, even if LangChain is stateless by default. The agent uses this context—the user's profile and their history—to build highly relevant prompts for the final `message_ai_chatbot` call.

Setup guide

Set up SmartChatAI MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes SmartChatAI tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "smartchatai-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent SmartChatAI transactions"
    })
    print(result["messages"][-1].content)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by SmartChatAI. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect SmartChatAI now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about SmartChatAI MCP in LangChain

The MCP Server exposes all its tools as callable endpoints. Your LangChain agent treats each tool—like `list_ai_chatbots` or `message_ai_chatbot`—as a function it can decide to call during reasoning.

Yes. Because the MCP Server calls are exposed as distinct steps, you get full observability in your tracing platform. You'll see exactly which tool was called, what arguments it used, and what data came back.

Absolutely. You can reliably call `check_api_health` at the start of your chain to verify connectivity before attempting any complex operations, preventing runtime failures.

It handles three main types: raw text via `add_text_to_knowledge_base`, structured PDFs using `add_pdf_to_knowledge_base`, and URLs through `add_website_to_knowledge_base`.

This MCP Server manages bot configuration details, including the name of a bot (via `create_new_ai_bot`) and conversation transcripts retrieved by `get_bot_chat_history`.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript