How to Use the Beekeeper MCP in Google ADK

Q: How do I add the Beekeeper tools to my Google ADK agent?

You wrap the server URL in an McpToolset and pass it to your LlmAgent's tools parameter. Google ADK then introspects the MCP Server and makes all the Beekeeper tools, like sendmessage, available to your Gemini model.

Q: Does the Google ADK integration for Beekeeper support filtering tools?

Yes, the McpToolset has an optional toolnames filter. You can provide a list of tool names, like 'listposts', 'listusers', to expose only a specific subset of Beekeeper functions to your agent. This is good for creating specialized, single-purpose agents.

Run enterprise agents on Beekeeper with Google ADK. Connect your Gemini model to manage users, posts, and messages on Google Cloud.

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 Google ADK

Create your Vinkius account to connect Beekeeper to Google ADK 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 Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Query Beekeeper Users at Scale

The Beekeeper MCP Server gives your Google ADK agent direct access to your company's user directory. You can `list_users` to get a complete directory or use `search_users` to pinpoint individuals. This is essential for agents that need to map frontline workers to tasks or data from other systems. Imagine your agent gets a new dataset in BigQuery. It can now cross-reference that data with your Beekeeper user base, find the right people with `get_user`, and prepare to send them targeted updates. It connects your cloud data to your frontline team.

Manage Communication Streams via MCP

Your Gemini-powered agent can now read and write to your company's main communication channels. The `list_streams` tool discovers all active streams, and `list_posts` pulls the content from any of them. This gives your agent situational awareness of what's happening on the ground. More importantly, your agent can act. Use `create_post` to broadcast operational updates, safety alerts, or schedule changes directly into the relevant Beekeeper stream. Since ADK is built for Google Cloud, you can trigger these posts from a Pub/Sub message or a Vertex AI pipeline.

Automate Messaging with a Google ADK Agent

This MCP server gives you the tools for automated messaging. The `send_message` tool lets your agent start one-on-one conversations with any user. Your agent can send reminders, ask for status updates, or deliver personalized information derived from your Google Cloud data. Your agent can also use `list_messages` to check for replies in a conversation. This lets you build simple, two-way interactions. The long context of Gemini models means the agent can hold the history of these conversations to provide more relevant follow-ups.

Setup guide

Set up Beekeeper MCP in Google ADK

Prerequisites

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

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with Beekeeper tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="Beekeeper_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Beekeeper tools via MCP.",
    tools=mcp_tools,
)

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 Google ADK

You wrap the server URL in an `McpToolset` and pass it to your `LlmAgent`'s `tools` parameter. Google ADK then introspects the MCP Server and makes all the Beekeeper tools, like `send_message`, available to your Gemini model.

Absolutely. That's a core use case. Your Google ADK agent can query BigQuery for information, then use the Beekeeper tools from this MCP integration to act on that information by communicating with your frontline teams.

Yes, the `McpToolset` has an optional `tool_names` filter. You can provide a list of tool names, like `['list_posts', 'list_users']`, to expose only a specific subset of Beekeeper functions to your agent. This is good for creating specialized, single-purpose agents.

Streams are for posts, like a company-wide announcement channel. The `create_post` and `list_posts` tools work with streams. Groups are collections of users, and `list_groups` helps you see how your teams are organized.

All requests containing your Beekeeper user information, posts, or messages are handled in isolated, short-lived environments. The Vinkius platform uses your single endpoint token for authentication and doesn't persist any of your company's communication data once the tool execution is complete.

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