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` tool instantly without leaving double messages.

Pumble MCP Server for OpenAI Agents SDK 10 tools — connect in under 2 minutes

Name: Pumble
Availability: InStock
Author: Vinkius

openai.github.io/openai-agents-python/mcp

Built by Vinkius GDPR 10 Tools SDK

The OpenAI Agents SDK enables production-grade agent workflows in Python. Connect Pumble through Vinkius and your agents gain typed, auto-discovered tools with built-in guardrails. no manual schema definitions required.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerStreamableHttp

async def main():
    # Your Vinkius token. get it at cloud.vinkius.com
    async with MCPServerStreamableHttp(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as mcp_server:

        agent = Agent(
            name="Pumble Assistant",
            instructions=(
                "You help users interact with Pumble. "
                "You have access to 10 tools."
            ),
            mcp_servers=[mcp_server],
        )

        result = await Runner.run(
            agent, "List all available tools from Pumble"
        )
        print(result.final_output)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Pumble MCP Server

Connect your Pumble workspace to any AI agent and bring powerful automation directly to your team's communication hub.

The OpenAI Agents SDK auto-discovers all 10 tools from Pumble through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns. chain multiple agents where one queries Pumble, another analyzes results, and a third generates reports, all orchestrated through Vinkius.

What you can do

Read & Manage Channels — List all public and private channels, fetch detailed metadata, and dynamically create new discussion channels on the fly
Message Operations — Retrieve conversation histories, post new messages, update typos, or delete outdated announcements seamlessly
Interactive Reactions — Add emoji reactions to messages automatically to acknowledge requests without cluttering the chat
User Directory — List all workspace users and pull detailed profiles (including emails and time zones) to ensure accurate tagging

The Pumble MCP Server exposes 10 tools through the Vinkius. Connect it to OpenAI Agents SDK in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Pumble to OpenAI Agents SDK via MCP

Follow these steps to integrate the Pumble MCP Server with OpenAI Agents SDK.

Install the SDK

Run pip install openai-agents in your Python environment

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token from cloud.vinkius.com

Run the script

Save the code above and run it: python agent.py

Explore tools

The agent will automatically discover 10 tools from Pumble

Why Use OpenAI Agents SDK with the Pumble MCP Server

OpenAI Agents SDK provides unique advantages when paired with Pumble through the Model Context Protocol.

Native MCP integration via `MCPServerSse`, pass the URL and the SDK auto-discovers all tools with full type safety

Built-in guardrails, tracing, and handoff patterns let you build production-grade agents without reinventing safety infrastructure

Lightweight and composable: chain multiple agents and MCP servers in a single pipeline with minimal boilerplate

First-party OpenAI support ensures optimal compatibility with GPT models for tool calling and structured output

Pumble + OpenAI Agents SDK Use Cases

Practical scenarios where OpenAI Agents SDK combined with the Pumble MCP Server delivers measurable value.

Automated workflows: build agents that query Pumble, process the data, and trigger follow-up actions autonomously

Multi-agent orchestration: create specialist agents. one queries Pumble, another analyzes results, a third generates reports

Data enrichment pipelines: stream data through Pumble tools and transform it with OpenAI models in a single async loop

Customer support bots: agents query Pumble to resolve tickets, look up records, and update statuses without human intervention

Pumble MCP Tools for OpenAI Agents SDK (10)

These 10 tools become available when you connect Pumble to OpenAI Agents SDK via MCP:

chat_add_reaction

Adds an emoji reaction to a message

chat_delete_message

This action is irreversible. Deletes a message from a Pumble channel

chat_history_messages

Retrieves recent messages from a channel

chat_post_message

Specify the channel ID and the message text. Sends a message to a Pumble channel

chat_update_message

Updates a pre-existing message

create_chat_channel

Specify name and whether it should be private. Creates a new communication channel

get_channel_info

Retrieves detailed information about a specific channel

get_user_info

Retrieves detailed information for a specific user

list_all_channels

Lists all public and private channels available in the workspace

list_workspace_users

Lists all users in the Pumble workspace

Example Prompts for Pumble in OpenAI Agents SDK

Ready-to-use prompts you can give your OpenAI Agents SDK agent to start working with Pumble immediately.

"List all our active channels in Pumble."

"Post a message in the #dev-updates channel stating that 'Deployment 2.1 is completed'."

"Read the last 3 messages from #marketing-q4 and react to the last one with a 'thumbsup'."

Troubleshooting Pumble MCP Server with OpenAI Agents SDK

Common issues when connecting Pumble to OpenAI Agents SDK through the Vinkius, and how to resolve them.

MCPServerStreamableHttp not found

Ensure you have the latest version: pip install --upgrade openai-agents

Agent not calling tools

Make sure your prompt explicitly references the task the tools can help with.

Pumble + OpenAI Agents SDK FAQ

Common questions about integrating Pumble MCP Server with OpenAI Agents SDK.

How does the OpenAI Agents SDK connect to MCP?

Use MCPServerSse(url=...) to create a server connection. The SDK auto-discovers all tools and makes them available to your agent with full type information.