How to Use the MaestroQA MCP in Google ADK

Q: How do I configure Google ADK to use the MaestroQA MCP Server?

You initialize McpToolset using the streamable HTTP parameters pointing to your Vinkius endpoint. Then, pass that toolset into your LlmAgent constructor. The agent automatically gains access to tools like listqarubrics to read your evaluation criteria.

Q: Can I restrict which MaestroQA tools the Google ADK agent can use?

Yes, you can use the optional toolnames filter when initializing your McpToolset in Python. This lets you restrict the agent to read-only tools like listqatickets and prevent it from running write operations.

Q: How does Google ADK handle large data exports from MaestroQA?

The agent uses requestqadataexport to start the export job asynchronously. Because Gemini can handle long contexts, once the agent gets the files via getexportdownloadlinks, it can process the entire dataset in a single reasoning step.

Connect MaestroQA to Google ADK to analyze support quality data alongside your BigQuery tables using Gemini's long context.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect MaestroQA MCP to Google ADK

Create your Vinkius account to connect MaestroQA 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 MaestroQA with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Analyze massive ticket histories with Google ADK

Your agent uses `list_qa_tickets` and `get_ticket_qa_details` via this MCP Server to pull large batches of support interactions for deep analysis. Gemini models excel at processing massive amounts of text in a single run, letting your agent inspect support quality alongside your internal documentation. The agent processes these logs within Gemini's long-context window to find patterns in support quality. You get deep analysis without hitting context limits or needing complex chunking strategies.

Export and pipe QA data directly into BigQuery

The `request_qa_data_export` tool lets your agent trigger massive historical exports directly from your Google Cloud environment. Enterprise support teams need their quality data where their analytics run. Once the export is ready, the agent retrieves the files with `get_export_download_links` and pipes them into BigQuery. This lets you join MaestroQA metrics with your warehouse data to build custom Looker dashboards.

Sync external performance metrics into MaestroQA

Your agent uses `push_csat_scores` and `list_qa_agents` to sync external performance metrics back into your QA platform. If you track customer satisfaction in an external database, your Google ADK agent can read those tables and write the scores back. The agent cross-references your active team members to make sure every score is mapped to the right person. This keeps your grading rubrics accurate and your performance dashboards updated.

Setup guide

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

You initialize `McpToolset` using the streamable HTTP parameters pointing to your Vinkius endpoint. Then, pass that toolset into your `LlmAgent` constructor. The agent automatically gains access to tools like `list_qa_rubrics` to read your evaluation criteria.

Yes, you can use the optional `tool_names` filter when initializing your `McpToolset` in Python. This lets you restrict the agent to read-only tools like `list_qa_tickets` and prevent it from running write operations.

The agent uses `request_qa_data_export` to start the export job asynchronously. Because Gemini can handle long contexts, once the agent gets the files via `get_export_download_links`, it can process the entire dataset in a single reasoning step.

Yes, you can register both your BigQuery tools and this MCP Server toolset under the same Google ADK agent. This allows the agent to pull ticket data with `get_ticket_qa_details` and immediately compare it against raw database records.

All API requests flow through an ephemeral, zero-trust MCP sandbox managed by Vinkius. The server only touches the specific QA rubrics, agent performance metrics, and CSAT scores you request. Your credentials are encrypted at rest and never exposed to the LLM or external networks.

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