How to Use the FlowUs MCP in Google ADK

Q: How do I register the FlowUs MCP Server with my Google ADK agent?

Instantiate McpToolset with the StreamableHttpServerParameters pointing to your Vinkius URL. Pass this toolset into your LlmAgent constructor to expose the workspace tools to Gemini.

Q: Can I restrict my Google ADK agent to read-only FlowUs tools?

Yes. Use the optional toolnames filter when initializing your McpToolset to only expose getpage and listpages, blocking write tools like updatepage.

Q: How does Google ADK handle large FlowUs database queries?

The agent uses querydatabase to retrieve rows in batches, which fits easily into the Gemini long-context window. This allows the model to process thousands of workspace records alongside your BigQuery datasets.

Q: How is user data secured inside the Google Cloud environment?

Workspace user profiles fetched via listusers are isolated within your private Google Cloud tenant. No telemetry logs or access lists are stored outside your designated VPC, keeping compliance intact.

Feed your Google ADK enterprise agents live FlowUs data via the MCP Server for long-context reasoning across millions of workspace tokens.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect FlowUs MCP to Google ADK

Create your Vinkius account to connect FlowUs 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 FlowUs with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Enterprise workspace search with Google ADK

This MCP Server connects Google ADK to your workspace, allowing Gemini to analyze deep page hierarchies using `get_page` and `list_pages`. The agent pulls raw text directly into its million-token context window to answer complex corporate queries. Because Gemini holds so much data, you can feed entire document structures retrieved via `list_blocks` directly into your prompt. The ADK handles the transport, leaving your agent free to synthesize insights without hitting context limits.

BigQuery data syncs to workspace databases

Your Google ADK agent pulls analytics from BigQuery and writes them to your workspace via `create_database_row`. The pipeline runs natively on Google Cloud infrastructure for reliable, automated reporting. Before writing, the agent calls `list_databases` and `get_database` to match the schema. If it finds a mismatch, it corrects the payload layout before executing the update, keeping your tables clean.

Automated wiki maintenance and user audits

The agent maintains your team documentation by calling `update_page` and `create_page` based on system alerts. You configure the `McpToolset` using your Vinkius HTTP endpoint to expose these MCP tools to your Vertex AI models. To keep your team directory accurate, the agent runs `list_users` to audit who has access to specific pages. It writes these audit logs directly to a dedicated compliance page in your workspace.

Setup guide

Set up FlowUs 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 FlowUs 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="FlowUs_agent",
    model="gemini-2.0-flash",
    instruction="You have access to FlowUs 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 FlowUs. 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 FlowUs 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 FlowUs MCP in Google ADK

Instantiate `McpToolset` with the `StreamableHttpServerParameters` pointing to your Vinkius URL. Pass this toolset into your `LlmAgent` constructor to expose the workspace tools to Gemini.

Yes. Use the optional `tool_names` filter when initializing your `McpToolset` to only expose `get_page` and `list_pages`, blocking write tools like `update_page`.

The agent uses `query_database` to retrieve rows in batches, which fits easily into the Gemini long-context window. This allows the model to process thousands of workspace records alongside your BigQuery datasets.

Yes, the ADK supports both. For cloud-deployed enterprise agents, the HTTP transport is recommended to connect securely to your hosted MCP on Vinkius.

Workspace user profiles fetched via `list_users` are isolated within your private Google Cloud tenant. No telemetry logs or access lists are stored outside your designated VPC, keeping compliance intact.

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