4,500+ servers built on MCP Fusion
Vinkius
Chatwoot logo
Vinkius
Mastra AI logo

How to Use the Chatwoot MCP in Mastra AI

Build bulletproof Chatwoot workflows that handle errors and retries automatically. Automate your customer support logic with Mastra AI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

Chatwoot MCP on Cursor AI Code Editor MCP Client Chatwoot MCP on Claude Desktop App MCP Integration Chatwoot MCP on OpenAI Agents SDK MCP Compatible Chatwoot MCP on Visual Studio Code MCP Extension Client Chatwoot MCP on GitHub Copilot AI Agent MCP Integration Chatwoot MCP on Google Gemini AI MCP Integration Chatwoot MCP on Lovable AI Development MCP Client Chatwoot MCP on Mistral AI Agents MCP Compatible Chatwoot MCP on Amazon AWS Bedrock MCP Support
MCP Servers - Free for Subscribers
Mastra AI

Connect Chatwoot MCP to Mastra AI

Create your Vinkius account to connect Chatwoot to Mastra AI 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

Automate Complex Support Logic

This MCP Server gives your Mastra AI agent the tools to manage Chatwoot from your backend. You can build workflows that check for new conversations with `list_woot_conversations`, get customer details using `get_contact_details`, and then take action based on your own business rules. Mastra's real power is in its conditional logic. For example: IF a conversation is from the 'Website' inbox, THEN get the full chat history with `get_chat_history` and summarize it, ELSE just send a first reply with `send_chat_message`. You define the entire sequence.

Reliable Message Delivery with Retries

APIs fail. It happens. With Mastra AI, you can wrap the `send_chat_message` tool in a retry block that uses exponential backoff. Your agent won't just give up if the Chatwoot API has a temporary glitch or network hiccup. This makes your automations far more resilient. You can design a workflow that attempts to send a message, and on failure, it uses `get_conversation_details` to check the conversation's status before trying again. If it still fails, it can trigger an alert.

Your Chatwoot MCP Server for Workflows

Connecting the Chatwoot tools to your Mastra agent is straightforward. It gives your agent a direct line to your customer support platform, equipped with all the functions needed to read and write data. These tools become the building blocks for your automated processes. A common pattern is listing all unassigned conversations with `list_woot_conversations`, looping through them, and then using `get_contact_details` to decide how to route them. This is how you build real automation, not just a simple bot.

Setup guide

Set up Chatwoot MCP in Mastra AI

Prerequisites

  • Node.js 18+ and a TypeScript project
  • @mastra/mcp + @mastra/core packages
  • Active Vinkius subscription with a valid endpoint token
  1. 1

    Install dependencies

    Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).

  2. 2

    Configure the MCPClient

    Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.

  3. 3

    Discover and inject tools

    Call mcpClient.listTools() and spread the result into your agent's tools object. All Chatwoot tools become native Mastra tools.

  4. 4

    Run with any model

    Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts
import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "chatwoot-mcp-client",
  servers: {
    "chatwoot-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "Chatwoot Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to Chatwoot tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent Chatwoot transactions"
);
console.log(result.text);

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.

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 Mastra AI

You instantiate the `MCPClient` with your Vinkius server URL. After that, you call `mcpClient.listTools()` and spread the result into your agent's tool configuration. Mastra AI automatically handles the transport and execution.
Yes, that's a core feature of the framework. You can configure automatic retries with backoff for the `send_chat_message` tool. It ensures your automated messages get sent reliably, even if there are temporary network problems.
A classic example is an automated escalation workflow. An agent can monitor conversations, and if a message contains 'urgent' and hasn't been replied to in 5 minutes, it can use the Chatwoot tools to re-assign the ticket and notify a manager.
No. Vinkius handles the connection to the MCP Server. You just provide the single endpoint token when you configure the `MCPClient` in your code, and it's ready to go.
Your agent's requests, including any customer contact info or message text, are passed through a zero-trust proxy. The MCP server runs in an ephemeral V8 Isolate sandbox. No conversation data from Chatwoot is ever logged or stored by Vinkius.

Start using the Chatwoot MCP today

We host it, we monitor it, we maintain it. You just paste one token.

Built & Managed by Vinkius 30s setup 8 tools

We've already built the connector for Chatwoot. Just plug in your AI agents and start using Vinkius.

No hosting. No infrastructure. No complex setup.
All 8 tools are live and waiting. You're up and running in seconds.

Claude Claude
ChatGPT ChatGPT
Cursor Cursor
Gemini Gemini
Windsurf Windsurf
VS Code VS Code
JetBrains JetBrains
Vercel Vercel
+ other MCP clients

Vinkius gives your AI agents access to the full catalog of app connectors, all fully managed, secure, and enterprise-ready. One subscription, every tool you need.

Zero hosting required Full MCP catalog included Enterprise-grade security Auto-updated by Vinkius

Built, hosted, and secured by Vinkius. You just connect and go.