How to Use the Looker (Business Intelligence & Data) MCP in Pydantic AI

Validate your Looker BI queries and dashboard metadata at runtime with Pydantic AI.

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 Pydantic AI

Create your Vinkius account to connect Looker (Business Intelligence & Data) to Pydantic AI 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe Looker metadata extraction with Pydantic AI

Working with loose JSON from BI tools often leads to silent failures when field types change. This MCP Server integrates with Pydantic AI to validate every dashboard list and folder structure at runtime. When your agent calls `list_dashboards` or `list_folders`, the incoming data is strictly validated against Pydantic models. If Looker returns an unexpected null value or an altered schema, your application fails loudly and immediately, preventing corrupted data from reaching your downstream workflows.

Run and validate inline queries safely

Executing raw queries dynamically can break your frontend if the data types do not match your expectations. By using `run_inline_query`, your agent fetches literal dimensions dynamically while Pydantic AI enforces strict type constraints on the output. This ensures that every metric returned by the query conforms to your application's data models. If a dimension that should be an integer suddenly arrives as a string, the framework flags it before your agent can make decisions based on bad data.

Audit report configurations with zero hallucinations

Agents can hallucinate metrics when reading raw text descriptions of dashboards. This integration allows your agent to fetch exact configurations using `get_dashboard`, `get_look`, and `list_looks` to get the ground truth. Because the tool responses are validated, the agent can reliably map out the lineage of your data. It matches folders retrieved via `list_folders` with content found in `search_content` to build an accurate, validated map of your entire BI setup.

Setup guide

Set up Looker (Business Intelligence & Data) MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "looker-business-intelligence-data-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Looker (Business Intelligence & Data) tools.",
)

result = await agent.run("List recent Looker (Business Intelligence & Data) transactions")
print(result.output)

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 Pydantic AI

Install the pydantic-ai-slim package with MCP support, then initialize the MCPToolset with your server's HTTP endpoint. Pass this toolset directly to your Agent constructor to expose tools like `list_dashboards` and `run_inline_query` with built-in runtime validation.

Pydantic AI will raise a validation error immediately. This prevents your agent from working with malformed BI metadata or incorrect query results, ensuring your application only processes clean, structured data.

Yes. Pydantic AI is model-agnostic, meaning you can connect this MCP Server to local models or commercial APIs. The runtime validation of tools like `get_dashboard` remains active regardless of which LLM you choose.

Pydantic AI supports both transport mechanisms through its unified MCPToolset class. You simply provide the server's URL, and the framework manages the underlying connection to run your Looker queries.

Your credentials and query payloads are processed inside an isolated V8 sandbox. This setup ensures that your Looker dashboard configurations, folder structures, and inline query results are never cached, logged, or exposed outside your secure 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