How to Use the ChatBot.com MCP in LangChain

Q: How do I pass ChatBot.com story states into a LangChain conversational agent?

Use the listchatbotstories tool inside your LangChain agent's tool list. The agent calls this tool to retrieve the active story map and injects the current step directly into its system prompt template.

Q: How does LangChain trace ChatBot.com MCP Server tool executions in LangSmith?

Every time your LangChain agent triggers liststoryinteractions, LangSmith logs the inputs, outputs, and latency. This gives you complete visibility into how the agent navigates your chatbot's conversational nodes.

Q: Where does my ChatBot.com user data and webhook URLs go during execution?

Your webhook configurations from listchatbotwebhooks and user profiles from getchatbotuserdetails process locally inside Vinkius's isolated sandbox. No user interaction history or webhook tokens are ever stored or sent to external logging servers.

Run multi-step LangChain reasoning loops that inspect ChatBot.com stories and adapt conversations on the fly.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect ChatBot.com MCP to LangChain

Create your Vinkius account to connect ChatBot.com to LangChain and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup ChatBot.com with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Debug ChatBot.com story paths inside LangChain runs

The `list_chatbot_stories` tool exposes your entire bot conversation tree to your LangChain agent. Your agent queries this structure to map out active pathways before generating responses. LangChain chains together the output of `get_story_details` with your local vector databases. This lets you trace user progress through complex logic trees and log every step directly inside LangSmith.

Train ChatBot.com NLP entities via LangChain agents

The `list_chatbot_entities` tool pulls custom NLP matching patterns straight into your LangChain prompt templates. Your model reads these entities to verify incoming user intents against your production chatbot configuration. When users send unexpected phrases, this MCP Server feeds those inputs to `list_training_data` within your active chain. Your agent then suggests structural fixes, reducing fallback rate without leaving your Python run.

Track user interactions to branch LangChain logic

The `list_chatbot_users` tool pulls metadata for active bot contacts directly into your LangChain agent memory. Your chain checks user histories to decide whether to trigger an automated path or hand off to a human. Combining `get_chatbot_user_details` with LangGraph state nodes lets you build conditional routers. This MCP Server integration ensures your agent routes the current conversation based on real-time user status.

Setup guide

Set up ChatBot.com 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 ChatBot.com 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({
    "chatbotcom-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 ChatBot.com 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 ChatBot. 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 ChatBot.com 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 ChatBot.com MCP in LangChain

Use the `list_chatbot_stories` tool inside your LangChain agent's tool list. The agent calls this tool to retrieve the active story map and injects the current step directly into its system prompt template.

Yes, you can build a chain that reads unrecognized user inputs using `list_training_data`. Your LangChain model processes these phrases and outputs structured suggestions for your training pipeline.

Every time your LangChain agent triggers `list_story_interactions`, LangSmith logs the inputs, outputs, and latency. This gives you complete visibility into how the agent navigates your chatbot's conversational nodes.

Yes, LangChain allows you to mix this MCP Server with database or search tools. Your agent dynamically chooses whether to pull a user record via `get_chatbot_user_details` or query your internal database.

Your webhook configurations from `list_chatbot_webhooks` and user profiles from `get_chatbot_user_details` process locally inside Vinkius's isolated sandbox. No user interaction history or webhook tokens are ever stored or sent to external logging servers.

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