Pumble Connector for AI agents.
10 live capabilities
Automate your team communication and workspace management.
Waiting for input…
Why people use Pumble
Pumble Workspace Automation for Engineering Teams
With this Connector, that manual cycle disappears. Your agent can monitor your workflows and use chat_post_message to announce results the moment they happen. You get a workspace that updates itself, keeping everyone in the loop without anyone having to lift a finger.
What Vinkius changes
It turns your team chat into a controllable workspace for your AI agent.
Use it from Claude, ChatGPT, Cursor or another AI client you already have.
One account · 5,900+ Connectors
- Real-world use case 01
Automated Deployment Alerts
A DevOps engineer wants a message in a specific channel every time a build finishes.
- Real-world use case 02
Onboarding Automation
An Ops lead needs to create five new channels for a new client.
- Real-world use case 03
Community FAQ Scanning
A community manager asks the agent to scan a support channel for common issues.
Complete set · 10capabilities
The complete Pumble capability set.
These are the exact actions your AI can choose when you ask it to work with Pumble.
01—04
4 capabilities in this set.
Part of 10 available through Pumble.
- 01 Capability
Chat history messages
Retrieve recent messages from a channel. This gives your agent the context it needs to answer questions or summarize logs.
- 02 Capability
Chat post message
Send a message to a Pumble channel. You just provide the channel ID and the text to get the word out.
- 03 Capability
Chat update message
Update a message you already sent. This is perfect for fixing typos or updating a status without sending a second message.
- 04 Capability
Create chat channel
Create a new communication channel. You can specify the name and whether it should be private.
05—07
3 capabilities in this set.
Part of 10 available through Pumble.
- 05 Capability
Get channel info
Retrieve detailed information about a specific channel. This helps the agent understand the context of a workspace area.
- 06 Capability
Get user info
Retrieve detailed information for a specific user. It pulls profiles including emails and time zones for accurate tagging.
- 07 Capability
List all channels
List all public and private channels available in the workspace. Use this to map out the whole team's communication structure.
08—10
3 capabilities in this set.
Part of 10 available through Pumble.
- 08 Capability
List workspace users
List all users in the Pumble workspace. This is the fastest way to see who is currently on the team.
- 09 Capability
Chat add reaction
Add an emoji reaction to a message. This lets your agent acknowledge a request without sending a new notification.
- 10 Capability
Chat delete message
Delete a message from a Pumble channel. Use this to clean up old announcements or remove mistakes.
Set up in minutes
One URL. Then ask Pumble to work.
Claude and ChatGPT only need the Connector URL. Copy it once, add it in settings, and use Pumble 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_4Sx6etxJF4y3fBjh6aBFRvVq4JmKLIrA6jdJWOmp/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 Pumble, and paste the URL above.
- Step 03
Turn it on in chat
Select +, open Connectors, and enable Pumble for the conversation.
ChatGPT · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_4Sx6etxJF4y3fBjh6aBFRvVq4JmKLIrA6jdJWOmp/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 Pumble URL.
- Step 03
Save and start
Save the connection and enable Pumble in your conversation. Desktop may ask you to restart once.
Cursor · IDE configuration
Advanced setup
{
"mcpServers": {
"pumble": {
"url": "https://edge.vinkius.com/vk_preview_4Sx6etxJF4y3fBjh6aBFRvVq4JmKLIrA6jdJWOmp/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 Pumble
Open Agent mode in chat and ask: "Using Pumble, help me...". 10 tools available
VS Code Copilot · IDE configuration
Advanced setup
{
"mcpServers": {
"pumble": {
"url": "https://edge.vinkius.com/vk_preview_4Sx6etxJF4y3fBjh6aBFRvVq4JmKLIrA6jdJWOmp/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 Pumble
Ask Copilot: "Using Pumble, help me...". 10 tools available
Windsurf · IDE configuration
Advanced setup
{
"mcpServers": {
"pumble": {
"url": "https://edge.vinkius.com/vk_preview_4Sx6etxJF4y3fBjh6aBFRvVq4JmKLIrA6jdJWOmp/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 Pumble
Open Cascade and ask: "Using Pumble, help me...". 10 tools available
Cline · IDE configuration
Advanced setup
{
"mcpServers": {
"pumble": {
"url": "https://edge.vinkius.com/vk_preview_4Sx6etxJF4y3fBjh6aBFRvVq4JmKLIrA6jdJWOmp/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 Pumble
Ask Cline: "Using Pumble, help me...". 10 tools available
Claude Code · Terminal command
Advanced setup
claude mcp add pumble --transport http "https://edge.vinkius.com/vk_preview_4Sx6etxJF4y3fBjh6aBFRvVq4JmKLIrA6jdJWOmp/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 Pumble
Ask Claude: "Using Pumble, show me...". 10 tools are ready
Where the request belongs
Work Pumble can move forward.
This is for team leads and engineers who are drowning in manual status updates and constant pings in their chat app.
DevOps Engineer
Automates deployment notifications and status updates to specific channels so the team stays informed without manual typing.
Community Manager
Scans history to answer common user questions and reacts to feedback to keep the community engaged.
Ops Lead
Provisions new project channels and broadcasts onboarding info instantly to keep new hires on track.
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.
Slack
Automate Slack messaging. send messages, search conversations, list channels and users directly from any AI agent.
Twist
Automate asynchronous communication workflows via Twist. manage workspaces, channels, threads, comments, and direct messages via any 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 Bot
Control and manage your Slack workspace. audit channels, messages, and users via AI.
Chanty
Automate team communication via Chanty. manage conversations, send messages, invite members, and update statuses using any AI agent.
Bring your own AI
Change the model, client or framework. Keep Pumble 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 Pumble.
The practical details behind the request, access and result.
Can the Pumble MCP create private channels?
Yes, the Pumble MCP can create both private and public channels. This allows your agent to set up secure areas for specific projects or sensitive team discussions automatically.
How does the Pumble MCP handle message history?
It retrieves recent messages from any channel in your workspace. This gives your agent the context it needs to answer questions about past projects or summarize recent discussions.
Can my agent react to messages?
Yes, your agent can add emoji reactions to messages. This is a great way to acknowledge tasks, give a thumbs up, or confirm receipt of information without cluttering the chat.
Can I use Pumble MCP to manage my team's user list?
Yes, you can use it to list all users in your workspace and get detailed profiles for specific individuals. This helps your agent identify the right people to tag or contact.
Does Pumble MCP support updating old messages?
Yes, the Pumble MCP can update existing messages. This is useful for correcting typos, updating a status, or changing a link in a post without having to send a new message.
Is it safe to let an agent delete messages?
Yes, the Pumble MCP includes a capability to delete messages. This is primarily used for cleaning up old announcements or removing mistakes to keep your workspace organized.
How do I securely obtain my API Key?
Installation in Pumble is unique. In your workspace, click + Add apps in the left sidebar, find the API addon, and install it. After doing so, go to any chat input box in Pumble and type /api-keys generate. A private, ephemeral message will appear containing your secret token. Paste that token here.
Can my AI automatically reply to unread issues?
Yes. You can instruct your agent to regularly fetch messages from a specific channel (chat_history_messages). The agent can evaluate questions, generate answers based on your knowledge base, and then use chat_post_message to post the solution back to the team instantly.
Is it possible for the AI to react with emojis?
Absolutely. It uses the chat_add_reaction functionality. A common use case is having the agent process a batch of tickets reported in Pumble, and instruct it to leave a '✅' checkmark reaction on the original message to signify that work is complete.
What happens if a bot message has a typo?
Unlike standard webhooks, this integration provides full bidirectional control. If your AI posted something incorrect, simply ask it to update its previous message. It will fetch its message ID and push a new payload using the chat_update_message capability instantly without leaving double messages.
One connection away
Give your agent a direct line to Pumble.
Connect Pumble once. Keep it beside 5,900+ managed Connectors when the next task needs more.
Explore every Connector No credit card required · Free tier available