How to Use the Looker (Business Intelligence & Data) MCP in Google ADK

Q: Can I restrict which Looker (Business Intelligence & Data) tools are exposed to my Google ADK agent?

Yes, Google ADK allows you to pass an optional toolnames filter when initializing your toolset. This lets you restrict your agent to read-only actions like listlooks while blocking structural tools like runinlinequery if needed.

Connect Gemini models to your Looker BI data using the Google ADK for enterprise analysis.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Looker (Business Intelligence & Data) MCP to Google ADK

Create your Vinkius account to connect Looker (Business Intelligence & Data) 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 Looker (Business Intelligence & Data) with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Expose Looker BI metadata to Google ADK agents

Gemini models shine when processing massive amounts of context. By connecting this MCP Server to your Google ADK setup, your agent can pull entire folder trees and dashboard lists using `list_folders` and `list_dashboards`. The model digests this structural metadata to understand your entire BI layout. When a user asks a complex question, the agent searches the instance using `search_content` to find the exact report containing the answers, rather than guessing.

Bridge Looker models and BigQuery data

Many enterprise setups run Looker on top of BigQuery. This MCP Server lets your agent run dynamic queries using `run_inline_query` to fetch dimensions directly from your Looker models. Your Google ADK agent can take these query results and join them with raw tables in BigQuery or feed them into Vertex AI models. This creates a loop where your agent verifies live business metrics against raw data warehouse records.

Analyze dashboard and look configurations

Stop manually digging through dashboard filters to find out how a metric is calculated. Your agent can use `get_dashboard` and `get_look` to extract the exact query mappings and filters. By calling `list_looks` and inspecting the results, the agent can summarize complex reports for business users. It extracts the raw query definitions, translates the dimensions, and explains the logic in plain English.

Setup guide

Set up Looker (Business Intelligence & Data) 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 Looker (Business Intelligence & Data) 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="Looker (Business Intelligence & Data)_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Looker (Business Intelligence & Data) 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 Looker. 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 Looker (Business Intelligence & Data) 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 Looker (Business Intelligence & Data) MCP in Google ADK

You install the Google ADK and initialize the MCP toolset with your server URL. Pass this toolset directly to your LlmAgent instance, which automatically exposes tools like `list_dashboards` and `run_inline_query` to your Gemini model.

Yes, Google ADK allows you to pass an optional tool_names filter when initializing your toolset. This lets you restrict your agent to read-only actions like `list_looks` while blocking structural tools like `run_inline_query` if needed.

Absolutely. Because Gemini models can handle over a million tokens, your Google ADK agent can use `get_dashboard` to pull highly detailed dashboard structures and analyze them all at once without running out of memory.

You define your Looker API credentials in your environment variables. The MCP Server handles the authentication securely in an isolated sandbox, so your Gemini models and Google Cloud agents never see your raw API keys.

The server communicates via secure transport protocols and only accesses the specific Looker dashboard configurations, folder structures, and query results you authorize. No data is stored permanently, and all operations occur within a zero-trust execution environment.

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