How to Use the Flow MCP in Google ADK

Q: How do I add the Flow MCP Server to Google ADK?

Initialize McpToolset with your Vinkius HTTP URL in Python. Pass that toolset object into your LlmAgent constructor to expose the project management tools to Gemini.

Q: Can Google ADK filter which Flow tools are exposed?

Yes, you can pass a toolnames list to the toolset parameter. This restricts Gemini to specific actions like addtaskcomment instead of exposing the entire suite.

Q: How does Google ADK run Flow queries on big datasets?

Gemini uses its long context to parse results from listtasks and listtaskcomments simultaneously. It processes thousands of task lines in a single call without hitting token limits.

Connect Gemini to your Flow projects with Google ADK to run large-context team automation directly from BigQuery.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Flow MCP to Google ADK

Create your Vinkius account to connect Flow 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 Flow with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Enterprise task analysis via Google ADK

This MCP Server connects Google ADK directly to your project boards using `list_tasks` and `get_task`. Gemini's million-token context window digests entire project histories to find blockers. You can pipe your BigQuery project metrics into the same agent context. The agent matches database records against live workspace data, updating priorities with `update_task` based on real-world engineering metrics.

Automatic project mapping with Google ADK

The Flow MCP Server allows Google ADK agents to map complex team hierarchies using `list_workspaces` and `list_projects`. Your agent scans active folders to align cloud infrastructure deployments with project boards. Once the agent identifies the correct project, it uses `list_task_lists` to find the right column. It then executes `create_task` to log deployment logs, keeping your engineering teams updated without manual updates.

Automated team updates via Google ADK

Your Google ADK agent monitors system alerts and uses `add_task_comment` to post updates directly to active tickets. The agent identifies the correct thread by running `list_task_comments` on specific task IDs. By querying `list_workspace_members`, the agent can tag the responsible engineer in the comment. This keeps your Google Cloud alerts tied directly to the people running the services.

Setup guide

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

Initialize `McpToolset` with your Vinkius HTTP URL in Python. Pass that toolset object into your `LlmAgent` constructor to expose the project management tools to Gemini.

Yes, you can pass a `tool_names` list to the toolset parameter. This restricts Gemini to specific actions like `add_task_comment` instead of exposing the entire suite.

Gemini uses its long context to parse results from `list_tasks` and `list_task_comments` simultaneously. It processes thousands of task lines in a single call without hitting token limits.

This integration supports both Stdio and Streamable HTTP transports. For hosted cloud agents, the Streamable HTTP transport connects your agent to the Vinkius endpoint.

Your project lists, task details, and member directories are isolated using Vinkius's ephemeral container system. Credentials are encrypted at rest, and the agent only interacts with the API through secure tokenized requests.

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