How to Use the ChatFly MCP in LangChain

Q: What's the best way to manage multiple ChatFly bots using LangChain?

Start with the listbots tool to get all your bot IDs. Then, use a map-reduce chain or an agent with a loop to run getbot or listdatasources on each one. This lets you perform checks or updates across your entire bot inventory.

Q: Which ChatFly tools are available in this MCP server?

You get seven tools. You can createbot, getbot, listbots, and updatebot to manage them. You can also listdatasources, uploaddatasource, and chat with your bots.

Build and manage your entire chatbot fleet with composable ChatFly tools and LangChain agents.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect ChatFly MCP to LangChain

Create your Vinkius account to connect ChatFly 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 ChatFly with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate Bot Deployment

The `create_bot` tool lets your agent spin up a new chatbot with a name and a welcome message. This is the first link in your deployment chain. From there, your LangChain agent takes the new bot's ID and passes it directly to the `upload_data_source` tool. That's how you build a sequence that doesn't just create a bot, but also immediately gives it the knowledge it needs to be useful.

Chain Your ChatFly MCP Server Tools

Use the `list_bots` tool to get a full inventory of your chatbots. Your agent can then iterate through that list, calling `get_bot` on each one to check its specific configuration. This lets you build maintenance chains. For instance, an agent could check all bots for a specific knowledge file using `list_data_sources` and then use `update_bot` to add it if it's missing. You're not just calling tools; you're building logic.

Test and Verify in One Go

The `chat` tool lets you test your bots directly from a LangChain agent. Your agent can hold a test conversation to verify the bot is working as expected after an update. This completes the cycle. You can build a single chain that uses `create_bot`, `upload_data_source`, `update_bot`, and then `chat` to run a full deployment and verification test. It's all done without any manual work.

Setup guide

Set up ChatFly 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 ChatFly 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({
    "chatfly-alternative-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 ChatFly 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 ChatFly. 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 ChatFly 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 ChatFly MCP in LangChain

Install the MCP adapter and point it to your Vinkius endpoint. Use the `get_tools()` method to load the ChatFly tools, then pass them to your agent. Your agent now has the context to use tools like `create_bot` and `list_bots`.

Yes, that's exactly what it's for. You'd have your agent call `create_bot`, get the new bot's ID from the output, and then feed that ID into the `upload_data_source` or `update_bot` tools as the next step in the chain.

Start with the `list_bots` tool to get all your bot IDs. Then, use a map-reduce chain or an agent with a loop to run `get_bot` or `list_data_sources` on each one. This lets you perform checks or updates across your entire bot inventory.

You get seven tools. You can `create_bot`, `get_bot`, `list_bots`, and `update_bot` to manage them. You can also `list_data_sources`, `upload_data_source`, and `chat` with your bots.

Your data is processed in a temporary, isolated environment. Vinkius ensures that any bot details, welcome messages, or data source content from your ChatFly calls are wiped clean the moment your LangChain agent's execution finishes. Nothing is stored.

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