How to Use the Aha! MCP in Google ADK

Q: How do I configure Aha! with Google ADK?

Use the McpToolset class to connect this MCP Server. Pass your Vinkius URL into StreamableHttpServerParameters, then hand that toolset to your LlmAgent initialization.

Q: Can Google ADK analyze all my Aha! releases at once?

Easily. Gemini's massive context window means you run listreleases and feed the entire output straight into the model without hitting token limits.

Connect Aha! to Google ADK to let your Gemini agents reason across massive product roadmaps.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Aha! MCP to Google ADK

Create your Vinkius account to connect Aha! 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 Aha! with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Cross-reference BigQuery and Aha!

Enterprise teams keep usage metrics in BigQuery and strategic goals in Aha!. Now your Gemini agent bridges that gap by pulling current product plans using `list_features` from the MCP Server. Because Gemini handles massive context windows, the agent ingests thousands of rows of analytics data and compares it directly against the feature definitions it just pulled.

Long-context roadmap analysis

Dump an entire quarter's worth of Aha! product releases into your agent's memory. It calls `list_releases` to grab the schedule, then reads through user feedback stored in Vertex AI through the MCP connection. The model processes all of it at once. It identifies gaps in your upcoming sprints and automatically suggests new backlog items by executing `create_idea`.

Filtered Google ADK toolsets

You don't always want agents writing to your Aha! product board. When configuring the integration, use the `tool_names` filter to restrict access to read-only operations like `get_feature` and `list_ideas`. This keeps your production environment safe. The agent gets the context it needs to answer stakeholder questions without the risk of accidentally modifying your core roadmap.

Setup guide

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

Use the `McpToolset` class to connect this MCP Server. Pass your Vinkius URL into `StreamableHttpServerParameters`, then hand that toolset to your `LlmAgent` initialization.

Easily. Gemini's massive context window means you run `list_releases` and feed the entire output straight into the model without hitting token limits.

Restrict the exposed tools. Apply a filter in your Google ADK setup so the agent only sees `list_features` instead of the full write suite.

It does. The integration supports both Stdio and HTTP transports, so your Vertex-hosted agents talk to the MCP endpoint without networking headaches.

Vinkius handles the connection using a zero-trust architecture. Your product features and release dates are processed in an ephemeral sandbox that requires a single endpoint token, keeping your BigQuery environment isolated from external credentials.

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