How to Use the Rocket.Chat MCP in Mastra AI

Q: Can a Mastra AI workflow send direct messages on Rocket.Chat?

Yes, the chatpostmessage tool sends direct messages to individual users when provided with their username. You can also use listdirectmessages to check active conversation threads before initiating a new one.

Build automated workflows that trigger Rocket.Chat alerts and manage channel memberships using Mastra AI and this MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Rocket.Chat MCP to Mastra AI

Create your Vinkius account to connect Rocket.Chat to Mastra AI — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Rocket.Chat with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Programmatic Alert Escalation

The `chat_send_message` tool routes automated alerts to target rooms based on specific pipeline events. If a deployment fails, your agent automatically drafts and sends the incident log to the engineering room. Mastra AI manages this flow using its built-in workflow engine, allowing you to build multi-step conditional alerts. If the first message does not get a response, the engine triggers secondary escalations without human intervention.

Automated Workspace Management via MCP Server

The `list_private_groups` and `list_public_channels` tools let your agents map out your workspace structure dynamically. The agent checks these collections to verify if a dedicated channel already exists for a project. Combining these tools with Mastra's retry logic ensures your automated setups do not fail due to temporary network drops. The system retries failed lookups with exponential backoff before throwing an error.

Human-in-the-Loop Message Moderation

The `chat_delete_message` tool allows your moderation agents to remove non-compliant content from any channel. It requires the precise room ID and message ID to execute. By using the Mastra AI tool approval feature, you can require a human administrator to confirm the deletion before the tool runs. This prevents accidental data loss while maintaining automated scanning.

Setup guide

Set up Rocket.Chat 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

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

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All Rocket.Chat tools become native Mastra tools.
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: "rocketchat-mcp-client",
  servers: {
    "rocketchat-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

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

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

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 Rocket.Chat. 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 Rocket.Chat 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 Rocket.Chat MCP in Mastra AI

Initialize the client with your server URL, then call the list tools method to register them. You can spread these tools directly into your agent configuration array. The framework handles the MCP transport negotiation automatically.

Yes, the `chat_post_message` tool sends direct messages to individual users when provided with their username. You can also use `list_direct_messages` to check active conversation threads before initiating a new one.

The framework runs tool executions inside a managed workflow block that supports automatic retries. If the server returns a rate limit or a timeout, the system backs off and tries again. You can configure the exact retry count in your agent setup.

No, the connection uses standard MCP SSE or HTTP transports out of the box. You only need to provide the endpoint URL and your access token. The client handles the underlying handshake and session management.

All message payloads, usernames, and private channel lists are processed in memory and never written to disk. The Vinkius MCP runtime isolates each connection session in an ephemeral container. Your credentials and chat tokens remain encrypted at rest and are only used to sign direct API requests.

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