Rocket.Chat Connector for AI agents.
10 live capabilities
Send messages and manage team chat rooms directly from your AI client.
Waiting for input…
Why people use Rocket.Chat
Rocket.Chat for Automated Team Communication
With this Connector, you can just tell your agent to handle it. It can post the updates, find the right team member, and summarize the room's activity in seconds. You get your time back.
What Vinkius changes
You get a way for your AI to act as a functional member of your team's chat workspace.
Use it from Claude, ChatGPT, Cursor or another AI client you already have.
One account · 5,900+ Connectors
- Real-world use case 01
Onboarding new team members
A new hire joins the company.
- Real-world use case 02
Finding the right point of contact
A user asks who handles billing.
- Real-world use case 03
Automated system alerts
A server goes down.
Complete set · 10capabilities
The complete Rocket.Chat capability set.
These are the exact actions your AI can choose when you ask it to work with Rocket.Chat.
01—04
4 capabilities in this set.
Part of 10 available through Rocket.Chat.
- 01 Capability
Chat update message
Edits the text of a message you already sent. It lets your agent fix typos or update details on the fly.
- 02 Capability
Get channel info
Pulls the details of a specific channel. Use it to see what a room is for or who manages it.
- 03 Capability
Get user info
Gets the profile and role of a specific user. It helps the agent identify who is who in your company.
- 04 Capability
List direct messages
Shows all your active 1-on-1 chat rooms. Use this to see your current private conversations.
05—07
3 capabilities in this set.
Part of 10 available through Rocket.Chat.
- 05 Capability
List private groups
Lists the private channels you are a member of. It helps the agent see your restricted workspace.
- 06 Capability
List public channels
Shows every public channel in your workspace. Use this to map out the whole team's chat structure.
- 07 Capability
List users
Pulls the full user directory from your workspace. This lets the agent find anyone in the organization.
08—10
3 capabilities in this set.
Part of 10 available through Rocket.Chat.
- 08 Capability
Chat delete message
Deletes a specific message from a room using its ID. This is helpful for removing mistakes or sensitive info quickly.
- 09 Capability
Chat post message
Sends a new message to a channel or user by name. Use this for automated pings or general updates.
- 10 Capability
Chat send message
Sends a message to a specific room ID. This is the most reliable way to send targeted messages.
Set up in minutes
One URL. Then ask Rocket.Chat to work.
Claude and ChatGPT only need the Connector URL. Copy it once, add it in settings, and use Rocket.Chat from the conversation.
Choose your client
Live previewAdvanced clients IDE · CLI
Claude · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_yQ6m4Hc2pUKZNoymv5FyFVr2aGg8ouh0Sbbph3gQ/mcp - Step 01
Open Connectors
In Claude Web or Claude Desktop, open Settings and choose Connectors.
- Step 02
Add the URL
Choose Add custom connector, name it Rocket.Chat, and paste the URL above.
- Step 03
Turn it on in chat
Select +, open Connectors, and enable Rocket.Chat for the conversation.
ChatGPT · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_yQ6m4Hc2pUKZNoymv5FyFVr2aGg8ouh0Sbbph3gQ/mcp - Step 01
Open MCP settings
On desktop, open Settings and MCP servers. On web, open your workspace app or connector settings.
- Step 02
Add the URL
Choose Add server with Streamable HTTP, or create a custom MCP app, then paste the Rocket.Chat URL.
- Step 03
Save and start
Save the connection and enable Rocket.Chat in your conversation. Desktop may ask you to restart once.
Cursor · IDE configuration
Advanced setup
{
"mcpServers": {
"rocketchat": {
"url": "https://edge.vinkius.com/vk_preview_yQ6m4Hc2pUKZNoymv5FyFVr2aGg8ouh0Sbbph3gQ/mcp"
}
}
}- Step 01
Open MCP Settings
Press Cmd+Shift+P (macOS) or Ctrl+Shift+P (Windows/Linux) → search "MCP Settings"
- Step 02
Add the server config
Paste the JSON configuration above into the mcp.json file that opens
- Step 03
Save the file
Cursor will automatically detect the new Connector
- Step 04
Start using Rocket.Chat
Open Agent mode in chat and ask: "Using Rocket.Chat, help me...". 10 tools available
VS Code Copilot · IDE configuration
Advanced setup
{
"mcpServers": {
"rocketchat": {
"url": "https://edge.vinkius.com/vk_preview_yQ6m4Hc2pUKZNoymv5FyFVr2aGg8ouh0Sbbph3gQ/mcp"
}
}
}- Step 01
Create MCP config
Create a .vscode/mcp.json file in your project root
- Step 02
Add the server config
Paste the JSON configuration above
- Step 03
Enable Agent mode
Open GitHub Copilot Chat and switch to Agent mode using the dropdown
- Step 04
Start using Rocket.Chat
Ask Copilot: "Using Rocket.Chat, help me...". 10 tools available
Windsurf · IDE configuration
Advanced setup
{
"mcpServers": {
"rocketchat": {
"url": "https://edge.vinkius.com/vk_preview_yQ6m4Hc2pUKZNoymv5FyFVr2aGg8ouh0Sbbph3gQ/mcp"
}
}
}- Step 01
Open MCP Settings
Go to Settings → MCP Configuration or press Cmd+Shift+P and search "MCP"
- Step 02
Add the server
Paste the JSON configuration above into mcp_config.json
- Step 03
Save and reload
Windsurf will detect the new server automatically
- Step 04
Start using Rocket.Chat
Open Cascade and ask: "Using Rocket.Chat, help me...". 10 tools available
Cline · IDE configuration
Advanced setup
{
"mcpServers": {
"rocketchat": {
"url": "https://edge.vinkius.com/vk_preview_yQ6m4Hc2pUKZNoymv5FyFVr2aGg8ouh0Sbbph3gQ/mcp"
}
}
}- Step 01
Open Cline MCP Settings
Click the Connectors icon in the Cline sidebar panel
- Step 02
Add remote server
Click "Add Connector" and paste the configuration above
- Step 03
Enable the server
Toggle the server switch to ON
- Step 04
Start using Rocket.Chat
Ask Cline: "Using Rocket.Chat, help me...". 10 tools available
Claude Code · Terminal command
Advanced setup
claude mcp add rocketchat --transport http "https://edge.vinkius.com/vk_preview_yQ6m4Hc2pUKZNoymv5FyFVr2aGg8ouh0Sbbph3gQ/mcp"- Step 01
Install Claude Code
Run npm install -g @anthropic-ai/claude-code if not already installed
- Step 02
Add the Connector
Run the command above in your terminal
- Step 03
Verify the connection
Run claude mcp to list connected servers, or type /mcp inside a session
- Step 04
Start using Rocket.Chat
Ask Claude: "Using Rocket.Chat, show me...". 10 tools are ready
Where the request belongs
Work Rocket.Chat can move forward.
The team lead who needs to send out company-wide updates without manual repetition, or the support specialist who spends too much time looking up internal contact details.
Team Lead
Sends automated welcomes to new hires and summarizes channel activity during weekly syncs.
Support Staff
Finds user roles and pings the right people instantly based on natural language requests from customers.
IT Operations
Pushes system logs and automated alerts directly to specific chat rooms using the agent.
Build the capability set
Add more capabilities.
Each Connector adds new actions and data without changing how you work.
Browse ConnectorsMattermost (Secure Team Collaboration)
Manage team collaboration via Mattermost. send messages, search channels, and audit team activities.
Sendbird
Manage Sendbird chat infrastructure. orchestrate users, channels, and moderation directly from your AI agent.
Flock
Manage team collaboration via Flock. send rich messages with FlockML, handle public channels and private groups, and search rosters directly from any AI agent.
Slack
Automate Slack messaging. send messages, search conversations, list channels and users directly from any AI agent.
Slack Bot
Control and manage your Slack workspace. audit channels, messages, and users via AI.
CometChat
Enable your AI agent to manage chat users, groups, and messages via the CometChat API.
Bring your own AI
Change the model, client or framework. Keep Rocket.Chat connected.
-
Claude -
ChatGPT -
Gemini -
Cursor -
VS Code -
Windsurf -
ZCode -
Cline -
Zed -
Continue -
Kiro -
Roo Code -
Zencoder -
Goose -
Void -
Augment Code -
Amp -
Qodo -
Tabnine -
Pieces -
Sourcegraph Cody -
JetBrains -
Warp -
Amazon Q -
Antigravity -
BoltAI -
Raycast -
Jan -
LM Studio -
AnythingLLM -
Open WebUI -
Msty -
Cherry Studio -
LibreChat -
TypingMind -
Chorus -
5ire -
n8n -
LangChain -
LlamaIndex -
CrewAI -
Vercel AI SDK
Before you connect
Questions about Rocket.Chat.
The practical details behind the request, access and result.
Can the Rocket.Chat MCP send messages for me?
Yes, it lets your AI agent post messages in channels or direct messages. You can use it to send automated updates, welcomes, or alerts without leaving your current AI client.
How do I use Rocket.Chat MCP to find employees?
The agent can scan your workspace directory to find team members, check their roles, and see if they are currently online. This makes it easy to find the right person for a task.
Does Rocket.Chat MCP work for private groups?
Yes, it can see the private channels you belong to. This allows your agent to help you manage restricted workspace communications and stay updated on private discussions.
Can the agent fix a typo in a message?
Yes, the agent can update the text of a message you already sent. This is perfect for correcting mistakes or updating information in a shared channel quickly.
Is Rocket.Chat MCP good for automated alerts?
It is excellent for pushing logs or notifications to specific rooms. You can have your agent monitor systems and post alerts directly into the appropriate chat channels.
How do I set up Rocket.Chat MCP?
You just need to provide your Rocket.Chat URL, your User ID, and an Auth Token from your profile's Personal Access Tokens section. Once connected, your agent is ready to go.
Can the assistant create new channels or invite new users to the Rocket.Chat workspace?
No. This capability 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.
One connection away
Give your agent a direct line to Rocket.Chat.
Connect Rocket.Chat once. Keep it beside 5,900+ managed Connectors when the next task needs more.
Explore every Connector No credit card required · Free tier available