How to Use the Culture Amp MCP in Google ADK

Q: How do I configure the Culture Amp MCP Server with Google ADK?

Install the google-adk package. Set up a StreamableHttpServerParameters object with your Vinkius URL, wrap it in an McpToolset, and pass it to your LlmAgent tools array.

Q: Can Google ADK agents cross-reference Culture Amp data with BigQuery?

Yes. Your agent can pull engagement metrics using getsurveydetails and immediately write that data into BigQuery tables for long-term storage. The massive context window of Gemini makes processing these large datasets simple.

Deploy Gemini-powered agents that analyze Culture Amp employee surveys alongside your BigQuery warehouse using Google ADK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Culture Amp MCP to Google ADK

Create your Vinkius account to connect Culture Amp 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 Culture Amp with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Analyze enterprise feedback at scale

Processing thousands of survey responses requires serious context window capacity. Gemini handles this effortlessly when paired with your HR data. Your Google ADK agent pulls massive datasets into memory and reasons across entire organizational hierarchies without dropping details. The agent executes `list_engagement_surveys` to grab recent cycles. From there, it calls `get_survey_details` and `list_analytics_datasets` to feed raw metrics into your Vertex AI pipelines. You get instant visibility into team morale without writing manual extraction scripts.

Map organizational structures

Keeping your Google Cloud identity systems synced with HR realities is notoriously difficult. This MCP Server bridges that gap by exposing your exact reporting lines to your Gemini agents. They audit group assignments and flag discrepancies automatically. By running `list_organizational_groups` and `list_employees`, the agent builds a complete graph of your workforce. When managers need their team's data, the agent uses `search_employees_by_name` to verify their identity before pulling the requested reports.

Plug Culture Amp into Google ADK

Connecting these systems via MCP takes just a few lines of Python. You initialize a `McpToolset` with your Vinkius endpoint parameters and hand it directly to your `LlmAgent`. The framework handles the HTTP transport natively. Sometimes you only want an agent to read data, not write it. You restrict the exposed operations by passing a `tool_names` filter. This ensures your agent only has access to `list_demographic_fields` and `get_employee_details`, strictly preventing it from calling `create_employee_record`.

Setup guide

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

Install the `google-adk` package. Set up a `StreamableHttpServerParameters` object with your Vinkius URL, wrap it in an `McpToolset`, and pass it to your `LlmAgent` tools array.

Yes. Your agent can pull engagement metrics using `get_survey_details` and immediately write that data into BigQuery tables for long-term storage. The massive context window of Gemini makes processing these large datasets simple.

You can restrict access easily. Pass an array of specific strings to the `tool_names` parameter in your toolset to prevent the agent from seeing certain endpoints.

Give your Gemini agent a name or email address. It automatically triggers `search_employees_by_name` to locate the correct profile within your directory.

Every request routes through an ephemeral V8 sandbox hosted by Vinkius. When your agent queries `list_demographic_fields` or pulls individual profiles, the memory state wipes immediately after the HTTP response. We never store your organizational hierarchies or survey results.

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