How to Use the Chatwoot MCP in LangChain

Q: How do I pass Chatwoot tools to a LangChain agent using MCP?

You install the langchain-mcp-adapters package and initialize the MultiServerMCPClient with the Vinkius endpoint. Call client.gettools() to retrieve tools like getchathistory and pass them directly to your agent constructor.

Q: Does this Chatwoot integration support LangChain's stateful sessions?

It does. By using client.session(), your LangChain graph maintains the active conversation ID across multiple turns while calling sendchatmessage to reply to the user.

Q: How do I handle multiple inboxes using this setup?

Your agent calls listchatwootinboxes to identify whether a conversation originated from WhatsApp, web chat, or email. LangChain routes the response logic through different formatting chains depending on that channel type.

Run multi-step support chains in LangChain using this Chatwoot MCP Server to read threads and write replies.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Chatwoot MCP to LangChain

Create your Vinkius account to connect Chatwoot 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 Chatwoot with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain customer lookup with historical context in LangChain

The `get_contact_details` tool fetches the customer's profile directly inside your LangChain runnable sequence. Your LangChain agent uses this identity data to branch its logic, routing premium clients to VIP queues without human intervention. Next, your LangChain chain feeds that profile into `get_chat_history` to pull recent Chatwoot interactions. LangSmith traces the entire flow, showing you exactly how the agent decided to format the Chatwoot response based on past friction.

Run Chatwoot MCP Server actions inside LangGraph pipelines

Running `list_woot_conversations` lets your LangChain agent scan active queues for unanswered customer tickets. It evaluates which Chatwoot threads require immediate attention by feeding the raw text into your custom LangChain prompt templates. Once the LangChain agent determines the priority, it triggers `get_conversation_details` to inspect the metadata. This keeps your Chatwoot support pipelines running on fresh, real-time data instead of stale database exports.

Send automated agent replies directly to active threads

The `send_chat_message` tool posts replies back to your customer through the exact Chatwoot channel they used to reach out. Your LangChain agent handles the draft generation, checks it against safety guidelines, and fires the message. Before sending, the LangChain agent runs `list_support_agents` to see who is currently online in Chatwoot. It can assign the Chatwoot ticket to an active human teammate if the customer's query requires complex troubleshooting.

Setup guide

Set up Chatwoot 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 Chatwoot 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({
    "chatwoot-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 Chatwoot 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 Chatwoot. 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 Chatwoot 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 Chatwoot MCP in LangChain

You install the `langchain-mcp-adapters` package and initialize the `MultiServerMCPClient` with the Vinkius endpoint. Call `client.get_tools()` to retrieve tools like `get_chat_history` and pass them directly to your agent constructor.

Yes, LangSmith automatically tracks every call made by this MCP Server, including `get_conversation_details`. You see the exact millisecond latency, token count, and raw payload for every customer support query.

It does. By using `client.session()`, your LangChain graph maintains the active conversation ID across multiple turns while calling `send_chat_message` to reply to the user.

Your agent calls `list_chatwoot_inboxes` to identify whether a conversation originated from WhatsApp, web chat, or email. LangChain routes the response logic through different formatting chains depending on that channel type.

Vinkius runs the Chatwoot MCP Server in an isolated V8 sandbox, preventing any exposure of your customer contact details and chat histories. Your LangChain code communicates directly over a secure, single-token HTTPS endpoint, meaning no raw support credentials ever leak to the LLM provider.

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