Rocket.Chat MCP. Manage Chat Messages, Groups, and Users via AI.
Gemini Works with every AI agent you already use
…and any MCP-compatible client
Just plug in your AI agents and start using Vinkius.
Rocket.Chat MCP Server connects your agent directly to the open-source team chat platform. Your AI client can now send, update, or delete messages in any channel, list private and public groups, find user details, and audit who's active across your entire workspace.
What your AI agents can do
Chat delete message
Deletes a specific message from a given room ID, requiring both IDs for execution.
Chat post message
Sends a new message to a channel or user using their visible names as destinations.
Chat send message
Sends a new message directly to a specific room, requiring the destination room's unique ID.
The agent can post new messages using chat_post_message or send directed messages via chat_send_message. It can also update existing text with chat_update_message or remove messages entirely using chat_delete_message.
The agent lists all users in the workspace directory (list_users) and retrieves detailed profile data for any specific user ID using get_user_info.
You can list every public channel available (list_public_channels), or map out all private groups you belong to (list_private_groups). Specific room details come from get_channel_info.
The agent checks and lists every active one-on-one direct message channel associated with your user account using list_direct_messages.
Ask AI about this MCP
Supported MCP Clients
Gemini Waiting for input…
Rocket.Chat MCP Server: 10 Tools for Comms Ops
These tools give your agent full control over the chat platform, allowing it to read user data, send messages, and audit channel structures directly.
019d75ffchat delete message
Deletes a specific message from a given room ID, requiring both IDs for execution.
019d75ffchat post message
Sends a new message to a channel or user using their visible names as destinations.
019d75ffchat send message
Sends a new message directly to a specific room, requiring the destination room's unique ID.
019d75ffchat update message
Modifies the visible text content of an existing message within a chat thread.
019d75ffget channel info
Retrieves detailed metadata and information for one specific channel ID.
019d75ffget user info
Pulls comprehensive profile details, including roles, for a single user using their unique ID.
019d75fflist direct messages
Returns a list of IDs representing all active one-on-one direct message rooms you are part of.
019d75fflist private groups
Lists the unique identifiers for every private group (channel) that your user account belongs to.
019d75fflist public channels
Returns a list of all public channels available across the entire workspace directory.
019d75fflist users
Retrieves a comprehensive list of every user currently registered in the overall workspace directory.
Choose How to Get Started
Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.
Build Your Own
Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.
- Import from OpenAPI, Swagger, or YAML specs
- Create Agent Skills with progressive disclosure
- Deploy to edge with MCPFusion framework
- Built in DLP, auth, and compliance on every call
- Real time usage dashboard and cost metering
- Publish to catalog or keep private
Make Your AI Do More
Start with Rocket.Chat, then connect any of our 4,700+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 4,700+ others, all in one place
- Add new capabilities to your AI anytime you want
- Every connection is secured and compliant automatically
- Track usage and costs across all your servers
- Works with Claude, ChatGPT, Cursor, and more
- New servers added to the catalog every week
What you can do with this MCP connector
Yo, listen up. The Rocket.Chat MCP Server hooks your agent right into the open-source team chat platform. Your AI client can now do way more than just talk; it can actually act inside your workspace—managing messages, auditing user profiles, and mapping out every single group you're in.
When you connect this, your agent gains hands-on control over communications. It handles sending new messages to any channel or individual using chat_post_message, or it can send a message straight to a specific room when you know the unique ID—that’s what chat_send_message does. You're not limited to just talking, either; if someone sends out some garbage and you gotta fix it, your agent uses chat_update_message to change the visible text of an existing post.
And if that message is pure trash? No sweat—it’ll use chat_delete_message to wipe it from a specific room ID.
Mapping out who's where and what channels exist is just as good. Your agent can list every public channel available across the entire workspace directory using list_public_channels. It knows all the private groups you belong to by listing their unique identifiers with list_private_groups. If you need the deep details on any specific chat room—the metadata, everything—you use get_channel_info for a given channel ID.
For direct conversations, your agent checks and spits out a list of IDs representing every active one-on-one direct message room it's part of via list_direct_messages.
Talking about people, the directory is wide open. Your agent can pull a comprehensive rundown of literally every user currently registered in the whole workspace with just list_users. If you need to know everything about one person—their roles, their profile details—it uses get_user_info for that specific user's unique ID.
Here’s how it works when your agent runs a complex task. You can tell your AI client: 'First, check the info for User X using get_user_info. Then, send an urgent message to the #alerts channel using chat_post_message, and finally, list every direct chat I'm in with list_direct_messages.' The agent executes that chain of commands natively.
It doesn't just read; it writes, it edits, and it deletes within your live Rocket.Chat environment. You get full operational control over communications, user data, and group structure—all through simple instructions to your AI client.
How Rocket.Chat MCP Works
- 1 Install the module in your MCP connectivity environment.
- 2 Go to your Rocket.Chat profile and generate a Personal Access Token (Auth Token).
- 3 Input your
Rocket.Chat URL, User ID, and Auth Token into the connection form.
The bottom line is that once configured with your authentication tokens, your agent can treat Rocket.Chat like another data source it runs commands against.
Who Is Rocket.Chat MCP For?
This tool serves Ops Engineers who are tired of manually switching between chat apps and dashboards to gather status updates. It's for Support Staff who need instant access to a colleague’s profile details without asking them directly, and for Team Leads who run announcements or audits across multiple channels daily.
Uses get_user_info to instantly look up a client's role or department when they mention a name in a ticket.
Runs system-wide commands, like sending an announcement across multiple public channels using chat_post_message, without navigating the UI.
Needs to audit who's in a specific private group or check channel activity by running get_channel_info and summarizing the data.
What Changes When You Connect
- Run full chat audits without clicking through tabs. Use
list_public_channelsfollowed byget_channel_infoto map out the entire conversation structure in minutes. - Stop hunting for user details. Passing a single ID to
get_user_infogives your agent their role, status, and profile data immediately. - Control the message flow exactly. Need to correct an announcement? Use
chat_update_message. If it's garbage, usechat_delete_message. - Handle team announcements programmatically. Instead of posting manually, tell your agent to run
chat_post_messagein#generaland tag the right people. - Keep track of private conversations easily. Run
list_direct_messagesto see every one-on-one chat room without manual navigation.
Real-World Use Cases
The Onboarding Announcement
A Team Lead has new hires and needs to announce them across three departments. Instead of jumping into each channel, they ask their agent: "Send a welcome message to #sales and thank the new team members." The agent calls chat_post_message for every target channel ID, executing the announcement in bulk.
The Colleague Lookup
A Support Agent needs to know if a user mentioned by a client is an Admin. They run: "Find out what role abCD123 has." The agent calls get_user_info, and the resulting data immediately confirms their 'Admin' status, allowing the agent to escalate correctly.
The Cleanup Crew
An Ops Engineer notices an old thread with sensitive info. They ask: "Delete that message from the #project-alpha channel." The agent uses chat_delete_message, requiring only the room ID and the specific message ID, ensuring no one sees it anymore.
Mapping Private Comms
A Project Manager needs to know every small working group that exists. They ask their agent: "List all my private groups." The agent calls list_private_groups, providing a complete map of every restricted 1-on-1 or team chat they're involved in.
The Tradeoffs
Assuming one tool does it all
Trying to send a message and then delete it using only chat_post_message. This is useless because you can't guarantee the IDs needed for cleanup.
→
You need two steps. First, run chat_post_message to get the confirmation ID of the sent message. Then, pass that specific ID and the room ID to chat_delete_message.
Asking for vague user names
Telling your agent: "Tell me about John." The system can't find him because it only works with IDs, not common names.
→
First, run list_users to get the definitive ID. Then, pass that specific ID into get_user_info for accurate data.
Assuming a list is enough
Calling list_public_channels and expecting full details on every single one without further action.
→
The list only gives names. You must select the channel name, and then call get_channel_info to pull all the deep metadata you need.
When It Fits, When It Doesn't
Use this server if your job requires coordinating actions across Rocket.Chat's entire feature set: sending messages, auditing users, or mapping group structures. It excels when you need your agent to perform multi-step workflows—for example, listing all private groups, and then getting the info for the top three of them. Don't use this if you only ever need basic chat history retrieval (that requires a different read API). Also, don't try to manage file sharing or call external systems; this is purely about user data and message state management within Rocket.Chat itself. If your goal is just reading messages, the list_direct_messages tool gets you started, but remember that for deep context, you'll need a follow-up on get_channel_info.
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.
VINKIUS INFRASTRUCTURE
Cloud Hosted
Managed infra
V8 Isolated
Sandboxed per request
Zero-Trust Proxy
No stored credentials
DLP Enforced
Policy on every call
GDPR Compliant
EU data residency
Token Compression
~60% cost reduction
Works with Claude, ChatGPT, Cursor, and more
The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.
This server provides 10 capabilities that interface natively with Claude, ChatGPT, Cursor, and any MCP client. No middleware. No custom integration required.
Available Capabilities
Manually tracking who's in every team chat sucks.
Right now, finding out which group has the right people for a project is a nightmare. You have to open the main channel, scroll through hundreds of messages, check the member list, and then maybe jump into another private group just to confirm roles. It’s clicks, context switching, and wasted minutes.
With this MCP server, your agent handles it in one prompt. Tell it to map the groups for Project X. The tool calls `list_private_groups` first, giving you all potential rooms. Then, if needed, `get_channel_info` pulls the member roster directly into the chat window. You get a definitive answer without leaving your workflow.
chat_update_message: Correcting announcements instantly.
If you send out an important announcement and realize you messed up a date or misspelled a key name, the old way is tedious. You'd have to find the original message in chat history, copy it, open a new draft, correct it manually, and then paste it back—losing context every step of the way.
Now, your agent handles it. You tell it: "Change the date on the last announcement." The tool uses `chat_update_message`, locating the message by ID and changing only the specified text. The change appears instantly, maintaining the original thread's history.
Common Questions About Rocket.Chat MCP
How do I list all public channels using chat_post_message? +
You don't use chat_post_message to list them. You must first run the list_public_channels tool. This returns a list of channel IDs and names, which you can then reference in subsequent commands.
What is the difference between chat_send_message and chat_post_message? +
chat_send_message requires a specific room ID. chat_post_message allows you to send messages using simple, human-readable names for the channel or user, which is generally easier.
Can I find out what group a user belongs to? +
You can list all private groups your account belongs to with list_private_groups. However, if you need details on who is in that group, you must call get_channel_info using the specific group ID.
How accurate is get_user_info for roles? +
The data retrieved by get_user_info provides detailed information about the user's assigned roles and status within your Rocket.Chat workspace, giving you an accurate view of their permissions.
What credentials does the `list_users` tool need to run? +
It requires a Personal Access Token and your Rocket.Chat URL for proper authentication. These details let your agent read user data securely, ensuring it has the right permissions to list everyone in the workspace.
What happens if `chat_update_message` fails? +
You must provide both a valid message ID and room ID. If either is wrong or the message was deleted, the API returns an error code. Your agent can then flag this failure and prompt you for corrected IDs.
How much detail does `get_channel_info` give? +
It pulls comprehensive metadata about a specific channel. You get details like the creation date, current member count, and if it's public or private. It gives you context way beyond just reading messages.
Are there rate limits when using `chat_send_message`? +
Yes, the API enforces standard rate limits to prevent overuse. If your agent sends too many messages in quick succession, it will receive a 429 error and needs to wait before trying again.
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.
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.
More in this category
Gupshup Messaging
Send WhatsApp messages, templates, media, and reactions via Gupshup API.
Slack
Manage channels, users, and send messages on Slack with AI agents.
Twilio
Automate communication workflows via Twilio — manage SMS messaging, voice calls, call recordings, and account usage directly from any AI agent.
You might also like
Luhn CC Validator
Stop LLMs from sending fake credit card numbers to payment gateways. Validates the mathematical Luhn check instantly.
Traefik Proxy
Monitor and manage your Traefik Proxy infrastructure — inspect routers, services, and middlewares directly from your AI agent.
Evolio
Transform your coaching practice with client tracking, session management, and progress analytics that help people grow.