How to Use the Rocket.Chat MCP in LangChain

Give your LangChain chains and ReAct agents direct control over Rocket.Chat rooms, messages, and user directories.

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 LangChain

Create your Vinkius account to connect Rocket.Chat to LangChain — 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Chain Rocket.Chat events into multi-step LangChain runs

Let your LangChain agent run wild across your Rocket.Chat workspace. It can call `list_public_channels` to find where the action is, read the room, and then use `chat_post_message` to drop an update. Every tool call acts as a discrete node in your LangGraph chains, passing real-time Rocket.Chat data directly into the next step. You don't have to hardcode your LangChain paths. The agent decides which Rocket.Chat channels need attention by pulling details with `get_channel_info` before updating an existing thread using `chat_update_message`. It's a live loop that keeps your team informed without human hand-holding.

Track every chat action with LangSmith observability

Debugging automated Rocket.Chat alerts in LangChain is usually a nightmare. This Rocket.Chat MCP Server exposes raw tool executions so you can track precisely why your LangChain agent chose to run `chat_delete_message` or who it looked up using `get_user_info`. You see the exact latency, token count, and payload of every single Rocket.Chat event inside your LangSmith dashboard. No more guessing why a Rocket.Chat notification failed to post in your LangGraph run. If `chat_send_message` returns an error, the exact room ID and payload are logged instantly in LangSmith, letting you fix broken agent logic before your team notices the silence.

Build automated directory sweeps with multi-server chains

Combine this Rocket.Chat toolset with databases or external APIs inside a single LangChain pipeline using our MCP Server. Your LangChain agent can query your database, check the active Rocket.Chat directory using `list_users`, and cross-reference active conversations via `list_direct_messages` to see who is currently online. Once it maps the active users, the LangChain agent can coordinate alerts across private spaces by calling `list_private_groups`. This turns your static Rocket.Chat workspace into an active participant in your LangChain deployment pipelines.

Setup guide

Set up Rocket.Chat 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 Rocket.Chat 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({
    "rocketchat-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 Rocket.Chat 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 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 LangChain

Install the adapter package and initialize the client using the Vinkius endpoint. Call the tool retrieval method to get the list, then pass those tools directly to your agent constructor. The agent will automatically decide when to run `chat_post_message` based on your prompt.

Yes, if the credentials you connect to Vinkius have the right permissions. Your LangChain agent can call `list_private_groups` to find private rooms and then read or write to them using `chat_send_message`.

If a tool call fails because of a missing room ID or bad message ID, the error is passed back to the LangChain run. The agent can catch this, inspect the error, and try a different tool or log the failure to your console.

Absolutely. You can filter the tools list returned by the server before passing them to your LangChain agent. If you don't want the agent deleting things, just strip out `chat_delete_message` from the toolset.

Vinkius runs the server in an isolated sandbox and handles all the API tokens securely. Your actual message text, channel names, and user directories are processed on the fly and never stored on our servers.

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