How to Use the Looker (Business Intelligence & Data) MCP in OpenAI Agents SDK

Run safe, multi-agent workflows across your Looker BI instance using the OpenAI Agents SDK.

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 OpenAI Agents SDK

Create your Vinkius account to connect Looker (Business Intelligence & Data) to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Expose Looker BI models to your OpenAI Agents SDK

Give your production agents direct access to your company's analytical structures. By registering this MCP Server, specialized agents can immediately locate where key metrics live using `list_folders` and `search_content`. You do not have to write custom glue code for every new dashboard or report. The agent auto-discovers these endpoints as standard tools. If an agent needs to inspect a specific metric, it queries the directory structure directly. This keeps your agentic workflows dynamic when folder names or content locations change.

Validate inline queries before execution

Running arbitrary queries on a database can be risky. This MCP Server lets your agent build and run queries on the fly using `run_inline_query`. Because you are using OpenAI's SDK, you can set strict pre-execution guardrails to inspect the query payload before it hits your Looker instance. This setup prevents your agent from requesting massive, unindexed tables that spike your database costs. If the query looks clean, the agent runs the raw dimensions and fetches the exact data points needed. You get full visibility of the execution path right inside your OpenAI developer dashboard.

Audit dashboard and look configurations

Agents can pull exact configurations of existing assets to verify data consistency. By invoking `get_dashboard` and `get_look`, your agent inspects the underlying query logic and filters behind your reports. This is useful when you want an agent to compare two different dashboards and find out why their numbers do not match. The agent pulls the target look object details through `list_looks` and `get_look` to trace the data lineage without human intervention.

Setup guide

Set up Looker (Business Intelligence & Data) MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Looker (Business Intelligence & Data) tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Looker (Business Intelligence & Data) tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Looker (Business Intelligence & Data) tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Looker (Business Intelligence & Data) Agent",
            instructions="You have access to Looker (Business Intelligence & Data) tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

You install the SDK, instantiate the streamable HTTP server with your connection URL, and pass it to your Agent constructor. The OpenAI Agents SDK automatically discovers the seven tools like `list_dashboards` and `run_inline_query` without manual schema definition.

Yes, you can control tool access at the SDK level by filtering the auto-discovered tools list before passing it to the Agent. This lets you restrict sensitive tools like `run_inline_query` to specific, highly trusted agents while leaving `list_dashboards` open to others.

Yes, every tool call executed by the MCP Server is tracked inside your OpenAI developer dashboard. You can trace exactly when an agent calls `get_dashboard` or runs a query, making it easy to debug agent behavior and monitor API latency.

We recommend setting the cacheToolsList parameter to true in your SDK configuration to avoid redundant schema lookups. For actual data queries, implement rate limiting at your agent's decision-making loop to prevent hitting Looker API thresholds.

The server only handles the specific Looker metadata, dashboard configurations, and query payloads you request. All credentials and data transfers run inside an isolated sandbox, meaning your proprietary database schemas and query results are never stored or exposed to third parties.

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