How to Use the Delighted MCP in Google ADK

Q: Can I restrict which Delighted tools my Google ADK agent sees?

The framework supports an optional toolnames filter. You specify exactly which operations the agent can access, keeping it focused on specific tasks like reading scores from the MCP Server.

Q: How does Gemini handle large Delighted survey exports?

Gemini ingests the entire output of listsurveyresponses into its massive context window. It reasons over thousands of comments simultaneously without losing details.

Q: Can I join Delighted scores with BigQuery data?

Your agent pulls the NPS metrics using getnpsmetricssummary. It then generates and executes BigQuery SQL to merge those scores with your internal revenue tables.

Feed Delighted survey data into your Google ADK agents. Analyze customer sentiment across millions of tokens using Gemini.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Delighted MCP to Google ADK

Create your Vinkius account to connect Delighted 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 Delighted with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Analyze Feedback with Google ADK

Passing thousands of survey responses to Gemini happens through the `list_survey_responses` tool. Your agent pulls raw scores, timestamps, and text comments directly into the massive context window for deep thematic analysis. Gemini reads the entire dataset at once instead of relying on chunked vector searches. It cross-references the output from `list_top_promoters` with your BigQuery customer data to identify exact usage patterns that drive high satisfaction.

Query Specific Customer Comments

The `search_responses_by_comment` tool lets your agent find exact keyword matches across your entire feedback database. When product managers ask about a specific feature, the agent fetches relevant quotes instantly. Combining this with `get_response_details` gives the agent full context on the user's setup and channel. It writes SQL queries to join this survey metadata with Vertex AI prediction models to forecast churn risk.

Trigger Surveys from GCP Events

Calling `add_person_to_survey` allows your agent to schedule feedback requests based on cloud infrastructure events. When a user completes a complex data migration, the agent automatically queues a targeted survey. Before sending, the agent runs `get_person_feedback_history` to verify past interactions. This prevents redundant outreach by checking the cumulative NPS contribution and existing metadata for that specific person.

Setup guide

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

Install google-adk via pip. Create an McpToolset using StreamableHttpServerParameters with your Vinkius URL, then pass it to the LlmAgent tools array.

The framework supports an optional tool_names filter. You specify exactly which operations the agent can access, keeping it focused on specific tasks like reading scores from the MCP Server.

Gemini ingests the entire output of list_survey_responses into its massive context window. It reasons over thousands of comments simultaneously without losing details.

Your agent pulls the NPS metrics using get_nps_metrics_summary. It then generates and executes BigQuery SQL to merge those scores with your internal revenue tables.

Reading feedback exposes raw customer comments and email addresses to the agent. The Vinkius zero-trust architecture ensures this payload travels from the MCP Server directly to your GCP environment without lingering in intermediate databases.

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