How to Use the Rocket.Chat MCP in LlamaIndex

Q: How do I index Rocket.Chat channels into a LlamaIndex vector store?

Use the MCP tool spec to pull data from listpublicchannels or listprivategroups. Convert the output into document objects, then pass them to your vector store indexer to make the conversations searchable.

Index your Rocket.Chat channels and user directories directly into LlamaIndex vector stores for semantic search.

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 LlamaIndex

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Feed live Rocket.Chat data into LlamaIndex RAG pipelines

Stop letting valuable team decisions get buried in Rocket.Chat history; pull them into LlamaIndex. This MCP Server lets your LlamaIndex agent pull raw workspace data using `list_public_channels` and convert those conversations into searchable vector embeddings. You can index active Rocket.Chat discussions into LlamaIndex and query them later to get answers grounded in real team chat. By using `get_channel_info` alongside your LlamaIndex document indexes, your agent can synthesize answers that combine static PDFs with live Rocket.Chat context. It keeps your LlamaIndex knowledge base fresh with actual Rocket.Chat updates without manual exports.

Query user directories and direct messages semantically

Finding the right expert on your team shouldn't require manual searching when LlamaIndex can query Rocket.Chat directories using this MCP Server. Your LlamaIndex agent can call `list_users` and `get_user_info` to build an indexed map of team skills and roles. When someone asks a question, the LlamaIndex agent searches this Rocket.Chat directory index to recommend the best contact. It can also scan active Rocket.Chat conversations using `list_direct_messages` and save that context to your LlamaIndex store. This connects your Rocket.Chat organizational chart directly to your LlamaIndex semantic search index.

Update workspace status based on index queries

This isn't a read-only LlamaIndex setup. When your LlamaIndex query engine detects a critical gap, the agent can use `chat_post_message` to post the finding directly to the relevant Rocket.Chat channel. It bridges the gap between static LlamaIndex search and active Rocket.Chat team coordination. If a status changes, the LlamaIndex agent can search for the previous alert and run `chat_update_message` to keep the Rocket.Chat channel clean. You get a self-updating log of Rocket.Chat activities powered by your LlamaIndex index.

Setup guide

Set up Rocket.Chat MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all Rocket.Chat MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to Rocket.Chat tools.",
)
response = await agent.run("List recent Rocket.Chat data")

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 LlamaIndex

Use the MCP tool spec to pull data from `list_public_channels` or `list_private_groups`. Convert the output into document objects, then pass them to your vector store indexer to make the conversations searchable.

Yes. The agent can use the index to find the exact message ID and then call `chat_update_message` to modify the text. This is useful for correcting outdated information in a channel.

Yes, as long as the user account configured on Vinkius has access. The agent can run `list_private_groups` to gather data from private spaces and index it just like public channels.

You can pass an allowed tools list when initializing the tool spec in your Python code. Simply omit `chat_delete_message` to ensure the agent can only read or post updates.

All API calls pass through the secure Vinkius sandbox. Your user directories and channel messages are processed in real-time and sent straight to your local or hosted LlamaIndex vector store without being cached by us.

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