How to Use the Beekeeper MCP in OpenAI Agents SDK

Q: Is this Beekeeper MCP server asynchronous for the OpenAI Agents SDK?

It is. You use an async with block to manage the server connection. This fits right into modern Python applications and lets your agent handle Beekeeper operations without blocking other tasks.

Q: What kind of tenant info can I get with gettenantinfo?

The gettenantinfo tool returns key details about your Beekeeper instance. This includes the tenant's name, URL, and unique ID. It's useful for agents that might operate across multiple tenants or need to confirm they're connected to the right one.

Connect your OpenAI Agent to Beekeeper. Manage posts, users, and messages with built-in safety checks and full tracing.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Beekeeper MCP to OpenAI Agents SDK

Create your Vinkius account to connect Beekeeper to OpenAI Agents SDK and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Beekeeper with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Manage Beekeeper Users and Groups

Your agent can pull user lists or search for specific people inside your Beekeeper tenant. Use `list_users` to get everyone, or `search_users` to find someone by name or email. The `get_user` tool then pulls their full profile, a direct way to find who you need to contact. Once you have a user, you can check their group memberships or list their conversations. The `list_groups` tool shows all available groups. The OpenAI Agents SDK provides guardrails, so you can set rules to prevent your agent from, say, pulling user data from the wrong tenant.

Control Posts and Streams with an MCP Server

This MCP Server connects your agent directly to Beekeeper's content streams. Your agent can call `list_streams` to see all the channels available in your organization. Then, use `list_posts` to read the latest updates from a specific stream. You can also have your agent publish content. The `create_post` tool lets it write a new post into any stream it has access to. Because you're using the OpenAI Agents SDK, every action is logged in your dashboard, giving you a clear audit trail of what your agent posted and when.

Send Direct Messages

Let your agent handle direct communication. The `send_message` tool sends a private message to any Beekeeper user ID. This is great for automated check-ins, sending alerts, or following up on tasks. You can also read conversations with `list_messages`. Combine these tools to build an agent that not only sends notifications but also reads replies to see if a human needs to step in. It's a closed loop for simple interactions.

Setup guide

Set up Beekeeper MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Beekeeper tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Beekeeper tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Beekeeper tools and returns structured results. Copy the full example on the right to get started.

agent.py

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

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Beekeeper Agent",
            instructions="You have access to Beekeeper tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 Beekeeper. 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 Beekeeper 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 Beekeeper MCP in OpenAI Agents SDK

It's automatic. When you pass the Beekeeper MCP Server to the Agent constructor, the SDK queries the server's endpoint, gets the list of available tools like `create_post`, and makes them available to your agent. No manual mapping needed.

Yes. The OpenAI Agents SDK lets you define guardrails and permissions. You can create policies that restrict the agent to specific tools, like only allowing it to `list_posts` but not `create_post`, for read-only access to Beekeeper.

It is. You use an `async with` block to manage the server connection. This fits right into modern Python applications and lets your agent handle Beekeeper operations without blocking other tasks.

The `get_tenant_info` tool returns key details about your Beekeeper instance. This includes the tenant's name, URL, and unique ID. It's useful for agents that might operate across multiple tenants or need to confirm they're connected to the right one.

Your Beekeeper user profiles, posts, and direct messages are processed within a V8 Isolate sandbox on Vinkius. We handle the auth token you provide, and all operations are ephemeral. The connection is secured, and your data isn't stored after the operation finishes.

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