Can the assistant create new channels or invite new users to the Rocket.Chat workspace?

No. This tool package is primarily focused on organic text-based communication, message manipulation (sending, modifying, deleting), and environment querying (listing what already exists). The generative capability to create workspace structural entities like 'new channels' or provisioning administrative user accounts is deactivated for baseline security in this module.

How does `chat_post_message` differ from `chat_send_message`?

`chat_send_message` uses a unique alphanumeric `Room ID` (e.g. 'cxyz123') to target an exact space unambiguously. Meanwhile, `chat_post_message` is designed to be human-readable, allowing your assistant to route messages to named destinations like '#general', '#dev-team', or directly to a user like '@johndoe'.

Can the AI edit or delete messages sent by other users?

Only if the authenticated account has the required admin or moderator permissions in the target channel. The AI inherits the same role-based restrictions as the user whose token is configured.

Rocket.Chat MCP Server for OpenAI Agents SDK 10 tools — connect in under 2 minutes

Name: Rocket.Chat
Availability: InStock
Author: Vinkius

openai.github.io/openai-agents-python/mcp

Built by Vinkius GDPR 10 Tools SDK

The OpenAI Agents SDK enables production-grade agent workflows in Python. Connect Rocket.Chat through Vinkius and your agents gain typed, auto-discovered tools with built-in guardrails. no manual schema definitions required.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerStreamableHttp

async def main():
    # Your Vinkius token. get it at cloud.vinkius.com
    async with MCPServerStreamableHttp(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as mcp_server:

        agent = Agent(
            name="Rocket.Chat Assistant",
            instructions=(
                "You help users interact with Rocket.Chat. "
                "You have access to 10 tools."
            ),
            mcp_servers=[mcp_server],
        )

        result = await Runner.run(
            agent, "List all available tools from Rocket.Chat"
        )
        print(result.final_output)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Rocket.Chat MCP Server

Connect your conversational assistant directly to Rocket.Chat, the open-source team communication platform. This integration transforms your AI into an active participant capable of chatting, sending notifications to channels, identifying active users, and auditing chat room data organically within your workspace.

The OpenAI Agents SDK auto-discovers all 10 tools from Rocket.Chat through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns. chain multiple agents where one queries Rocket.Chat, another analyzes results, and a third generates reports, all orchestrated through Vinkius.

What you can do

Communicate Actively — Instruct your assistant to post messages into public channels or private direct messages (chat_post_message, chat_send_message). Need to fix a typo? The AI can seamlessly edit (chat_update_message) or delete previous messages (chat_delete_message).
Explore Channels & Groups — Give your assistant vision over public discussions (list_public_channels) or private channels you belong to (list_private_groups). You can then extract deep information about specific rooms using get_channel_info.
Audit Users in the Network — Scan the entire user directory (list_users) to locate team members and review their roles and connection status directly (get_user_info).

The Rocket.Chat MCP Server exposes 10 tools through the Vinkius. Connect it to OpenAI Agents SDK in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Rocket.Chat to OpenAI Agents SDK via MCP

Follow these steps to integrate the Rocket.Chat MCP Server with OpenAI Agents SDK.

Install the SDK

Run pip install openai-agents in your Python environment

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token from cloud.vinkius.com

Run the script

Save the code above and run it: python agent.py

Explore tools

The agent will automatically discover 10 tools from Rocket.Chat

Why Use OpenAI Agents SDK with the Rocket.Chat MCP Server

OpenAI Agents SDK provides unique advantages when paired with Rocket.Chat through the Model Context Protocol.

Native MCP integration via `MCPServerSse`, pass the URL and the SDK auto-discovers all tools with full type safety

Built-in guardrails, tracing, and handoff patterns let you build production-grade agents without reinventing safety infrastructure

Lightweight and composable: chain multiple agents and MCP servers in a single pipeline with minimal boilerplate

First-party OpenAI support ensures optimal compatibility with GPT models for tool calling and structured output

Rocket.Chat + OpenAI Agents SDK Use Cases

Practical scenarios where OpenAI Agents SDK combined with the Rocket.Chat MCP Server delivers measurable value.

Automated workflows: build agents that query Rocket.Chat, process the data, and trigger follow-up actions autonomously

Multi-agent orchestration: create specialist agents. one queries Rocket.Chat, another analyzes results, a third generates reports

Data enrichment pipelines: stream data through Rocket.Chat tools and transform it with OpenAI models in a single async loop

Customer support bots: agents query Rocket.Chat to resolve tickets, look up records, and update statuses without human intervention

Rocket.Chat MCP Tools for OpenAI Agents SDK (10)

These 10 tools become available when you connect Rocket.Chat to OpenAI Agents SDK via MCP:

chat_delete_message

You must provide both room ID and message ID. Deletes a message from a room

chat_post_message

Sends a message to a channel or user by name

chat_send_message

Sends a message to a specific room by ID

chat_update_message

Updates the text of an existing message

get_channel_info

Retrieves details for a specific channel

get_user_info

Retrieves detailed information for a specific user

list_direct_messages

Lists all active direct message rooms

list_private_groups

Lists all private groups (channels) the user is a member of

list_public_channels

Lists all public channels in the workspace

list_users

Lists all users in the workspace directory

Example Prompts for Rocket.Chat in OpenAI Agents SDK

Ready-to-use prompts you can give your OpenAI Agents SDK agent to start working with Rocket.Chat immediately.

"List all of my active direct messages."

"Send a welcome message to #general thanking the new members."

"Find and get the user info for the ID abCD123."

Troubleshooting Rocket.Chat MCP Server with OpenAI Agents SDK

Common issues when connecting Rocket.Chat to OpenAI Agents SDK through the Vinkius, and how to resolve them.

MCPServerStreamableHttp not found

Ensure you have the latest version: pip install --upgrade openai-agents

Agent not calling tools

Make sure your prompt explicitly references the task the tools can help with.

Rocket.Chat + OpenAI Agents SDK FAQ

Common questions about integrating Rocket.Chat MCP Server with OpenAI Agents SDK.

How does the OpenAI Agents SDK connect to MCP?

Use MCPServerSse(url=...) to create a server connection. The SDK auto-discovers all tools and makes them available to your agent with full type information.