How to Use the Chatwoot MCP in AutoGen

Q: How do I register Chatwoot tools with AutoGen agents using MCP?

Use mcpservertools from the autogen-extmcp package to load the Vinkius server schema. Pass this tool list to your AssistantAgent constructor so the agent can invoke tools like sendchatmessage.

Q: Can AutoGen agents discuss Chatwoot conversation history?

Yes, one agent can call getchathistory and share the transcript in the group chat. The critic and writer agents then debate the best resolution strategy based on that historical transcript.

Q: How do AutoGen agents manage multiple Chatwoot inboxes?

The group coordinator agent runs listchatwootinboxes to map active channels. It then assigns specialized sub-agents to handle WhatsApp, email, or web chat tickets respectively.

Deploy AutoGen agents that debate support tickets and coordinate Chatwoot replies using this MCP Server.

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 AutoGen

Create your Vinkius account to connect Chatwoot to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Coordinate multi-agent ticket triage

The `list_woot_conversations` tool feeds unassigned tickets into your AutoGen conversation group. A triage AutoGen agent analyzes the text, while a routing agent suggests which team should handle the issue. They debate the Chatwoot priority level based on metadata fetched from `get_conversation_details`. Once the AutoGen agents reach a consensus, the group assigns the ticket to the right Chatwoot inbox.

Debate support resolutions before calling Chatwoot MCP Server

The `send_chat_message` tool is only triggered after your AutoGen agents agree on the best response. A writer AutoGen agent drafts the message, a critic agent reviews it for tone, and a safety agent checks for compliance. This multi-turn AutoGen debate ensures that no automated Chatwoot message goes out without rigorous internal verification. The final approved draft is posted back to the customer's Chatwoot thread.

Audit support agent workloads autonomously

The `list_support_agents` tool allows your supervisor AutoGen agent to check which team members are currently online. It balances the support load by comparing active Chatwoot agent availability with incoming ticket volumes. If one Chatwoot agent is overwhelmed, the AutoGen group coordinates with `get_contact_details` to reassign pending conversations. This ensures your AutoGen group reassigns pending conversations to under-utilized teammates.

Setup guide

Set up Chatwoot MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Chatwoot tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Chatwoot_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Chatwoot data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Chatwoot_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Chatwoot data")
    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 AutoGen

Use `mcp_server_tools` from the `autogen-ext[mcp]` package to load the Vinkius server schema. Pass this tool list to your `AssistantAgent` constructor so the agent can invoke tools like `send_chat_message`.

Yes, one agent can call `get_chat_history` and share the transcript in the group chat. The critic and writer agents then debate the best resolution strategy based on that historical transcript.

The group coordinator agent runs `list_chatwoot_inboxes` to map active channels. It then assigns specialized sub-agents to handle WhatsApp, email, or web chat tickets respectively.

Yes, the MCP adapter handles asynchronous execution out of the box. Your agents run concurrent checks using `list_woot_conversations` without blocking the main event loop.

It is never stored. Vinkius runs the MCP Server in an ephemeral sandbox environment, fetching support agent lists and inbox structures on demand. All credentials are encrypted, passing directly from your local AutoGen environment to the Chatwoot API.

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