How to Use the KanbanTool MCP in Google ADK

Q: How do I prevent the Google ADK from accidentally archiving KanbanTool cards?

Apply the toolnames filter when configuring the MCP Server connection. Simply omit archivetaskcard from the allowed list, and the ADK blocks the model from even seeing that the capability exists.

Feed KanbanTool MCP Server data into the Google ADK to let Gemini analyze massive board histories alongside your BigQuery datasets.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect KanbanTool MCP to Google ADK

Create your Vinkius account to connect KanbanTool 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 KanbanTool with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Map board bottlenecks with Gemini's context window

KanbanTool boards generate massive amounts of text. You feed the entire output of `list_board_tasks` and `list_task_activities` directly into Gemini's massive context window. The model ingests months of project history in a single shot. This MCP Server lets your Google ADK agent cross-reference task delays with your internal metrics. It pulls the board state via `get_board_details` and compares cycle times against incident reports sitting in BigQuery.

Execute Google ADK agent actions on cards

Analysis without action is useless. Once your Gemini agent identifies a systemic issue across your infrastructure, it instantly logs the work. It runs `create_task_card` to assign investigations to the right engineering team based on the data it found. You control the execution scope of the MCP Server. Use the tool_names filter in the McpToolset to expose only what you want. If you only want it to clean up old items, restrict it to `archive_task_card` and `update_task_details`.

Track team workloads across Google Cloud

Resource allocation requires knowing who is doing what. Your agent fetches current assignments using `get_user_profile` and `get_task_details`. It maps out exactly which developers are overloaded before assigning new BigQuery migration tasks. The integration supports both Stdio and HTTP transports natively. You deploy this on Cloud Run, and the agent continuously monitors your active projects via `list_boards` without dropping the connection.

Setup guide

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

Install google-adk via pip. Create an McpToolset passing your server URL into StreamableHttpServerParameters. Then, assign that toolset to the tools list when you instantiate your LlmAgent.

Yes. Because Gemini supports massive context windows, your agent runs list_task_activities across hundreds of cards and processes the entire text block simultaneously to find historical patterns.

Apply the tool_names filter when configuring the MCP Server connection. Simply omit archive_task_card from the allowed list, and the ADK blocks the model from even seeing that the capability exists.

Yes. Your Google Cloud agent runs a query, detects a spike in error rates, and automatically triggers create_task_card to put a high-priority bug on the engineering board.

The integration accesses raw task comments, cycle times, and board layouts via list_board_tasks. Vinkius routes these MCP Server requests through a stateless V8 Isolate. Your proprietary project metadata is processed in memory during the agent's execution phase and discarded immediately afterward.

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