Google Looker connector

1. Install the SDK

   Node.js

   npm install @scalekit-sdk/node

   Python

   pip install scalekit

   Full SDK reference: Node.js | Python

2. Set your credentials

   Add your Scalekit credentials to your .env file. Find values in app.scalekit.com > Developers > API Credentials.

   .env

   SCALEKIT_ENVIRONMENT_URL=<your-environment-url>
   SCALEKIT_CLIENT_ID=<your-client-id>
   SCALEKIT_CLIENT_SECRET=<your-client-secret>

3. Set up the connector

   Register your Google Looker credentials with Scalekit so it handles the token lifecycle. You do this once per environment.

   Dashboard setup steps

   Register your Scalekit environment with the Google Looker connector so Scalekit handles the OAuth flow and token lifecycle for you. The connection name you create will be used to identify and invoke the connection programmatically.

   1. Create a Google Looker instance

      Google Looker (Google Cloud core) runs as a managed service in your Google Cloud project. You must create an instance before setting up OAuth credentials.

      • Go to Google Cloud Console and select or create a project.

      • In the navigation menu, go to Looker (or search for “Looker” in the search bar).

      • Click Create Instance and follow the setup wizard. Note your instance hostname — it will look like your-company.cloud.looker.com. You will need this when adding connected accounts in Scalekit.

        

      Instance creation takes time

      A new Looker instance can take 30–60 minutes to provision. Wait until the status shows Active before proceeding.

   2. Create OAuth credentials in Google Cloud Console

      Google Looker uses Google OAuth 2.0. You need OAuth client credentials from the same Google Cloud project that hosts your Looker instance.

      • In Google Cloud Console, go to APIs & Services > Credentials.

      • Click Create Credentials > OAuth client ID.

      • Select Web application as the application type.

      • Copy the redirect URI from Scalekit (see next step) and paste it under Authorized redirect URIs.

      • Click Create. Copy the Client ID and Client Secret.

      Get the redirect URI first

      Open the Scalekit dashboard (step 3) to copy the redirect URI before creating the OAuth client. You can always edit the OAuth client to add the URI after creation.

   3. Add credentials in Scalekit

      • In Scalekit dashboard, go to AgentKit > Connections > Create Connection. Search for Google Looker and click Create.

        

      • Copy the Redirect URI shown on the configuration page. Go back to Google Cloud Console and add this URI to your OAuth client’s authorized redirect URIs.

      • Return to Scalekit and enter your credentials:

        • Client ID (from Google Cloud Console)
        • Client Secret (from Google Cloud Console)

        

      • Keep Access Type set to Offline to receive a refresh token for long-lived access.

      • Click Save.

   4. Add a connected account

      Each end-user who connects their Looker instance needs a connected account. The Looker Instance Hostname is required — this is the hostname of the Looker instance the user is accessing (without https://), for example your-company.cloud.looker.com.

      Via the Scalekit dashboard (for testing)

      • Go to Connected Accounts > Add Account.
      • Enter the User ID and Looker Instance Hostname, then click Save.
      • Complete the Google OAuth flow in the popup to authorize access.

      Via the SDK (for production)

      Generate an authorization link and redirect your user to it. After the user authorizes, Scalekit stores the token automatically.

      const { link } = await scalekit.actions.getAuthorizationLink({
        connectionName: 'googlelooker',
        identifier: 'user_123',
        state: { instanceUrl: 'your-company.cloud.looker.com' },
      })
      // Redirect the user to `link` to complete OAuth

4. Authorize and make your first call

   Node.js

   quickstart.ts

   import { ScalekitClient } from '@scalekit-sdk/node'
   import 'dotenv/config'
   
   const scalekit = new ScalekitClient(
     process.env.SCALEKIT_ENV_URL,
     process.env.SCALEKIT_CLIENT_ID,
     process.env.SCALEKIT_CLIENT_SECRET,
   )
   const actions = scalekit.actions
   
   const connector = 'googlelooker'
   const identifier = 'user_123'
   
   // Generate an authorization link for the user
   const { link } = await actions.getAuthorizationLink({ connectionName: connector, identifier })
   console.log('Authorize Google Looker:', link)
   process.stdout.write('Press Enter after authorizing...')
   await new Promise(r => process.stdin.once('data', r))
   
   // Make your first call
   const result = await actions.executeTool({
     connector,
     identifier,
     toolName: 'googlelooker_list_dashboards',
     toolInput: {},
   })
   console.log(result)

   Python

   quickstart.py

   import os
   from scalekit.client import ScalekitClient
   from dotenv import load_dotenv
   load_dotenv()
   
   scalekit_client = ScalekitClient(
       env_url=os.getenv("SCALEKIT_ENV_URL"),
       client_id=os.getenv("SCALEKIT_CLIENT_ID"),
       client_secret=os.getenv("SCALEKIT_CLIENT_SECRET"),
   )
   actions = scalekit_client.actions
   
   connection_name = "googlelooker"
   identifier = "user_123"
   
   # Generate an authorization link for the user
   link_response = actions.get_authorization_link(
       connection_name=connection_name,
       identifier=identifier,
   )
   print("Authorize Google Looker:", link_response.link)
   input("Press Enter after authorizing...")
   
   # Make your first call
   result = actions.execute_tool(
       tool_input={},
       tool_name="googlelooker_list_dashboards",
       connection_name=connection_name,
       identifier=identifier,
   )
   print(result)

What you can do

Connect this agent connector to let your agent:

• Run look, inline query — Run a saved Look and return the results in the specified format
• List models, looks, folders — List all available LookML models in the Looker instance
• Get look results, dashboard — Run a saved Look and return results in the specified format

Common workflows

Google OAuth consent screen verification

Before you use your own Google OAuth credentials in production, understand what end users see on Google’s consent screen when they authorize a connected account.

Audience type	Consent screen behavior	When to use
Internal	Shows your App Name and logo from Branding settings	Only users in your Google Workspace or Cloud Identity organization can authorize the connector
External	Shows {env_name}.scalekit.dev until Google verifies your app	Any user with a Google account can authorize the connector

Why External is required for most AgentKit connectors:

• Internal restricts authorization to users in your Google Workspace or Cloud Identity organization. Users with @gmail.com or other Google accounts outside your organization cannot complete OAuth.
• External is required when end users outside your organization authorize tool access through connected accounts.
• Organization-managed OAuth clients follow the same rules as personal or developer OAuth clients. Switching to an org-owned client does not bypass Google verification.
• Until Google completes verification of your External app, users see scalekit.dev on the consent screen. After verification, your App Name and logo appear.

Separate from Scalekit domain verification

This is Google’s OAuth consent screen behavior—not Scalekit’s. Custom domain controls your Scalekit environment URL for MCP auth branding. It does not replace Google’s app verification for OAuth consent screens.

During development:

• Add Test users under APIs & Services → OAuth consent screen while publishing status is Testing.
• On unverified apps, users can click Advanced → Go to app (unsafe) to proceed during testing.
• Google Workspace admins may need to allowlist your OAuth client.

For Google’s verification requirements and timeline, refer to Google’s OAuth consent screen verification guide.

Tool list

Use the exact tool names from the Tool list below when you call execute_tool. If you’re not sure which name to use, list the tools available for the current user first.

googlelooker_get_dashboard#Retrieve the full metadata of a Looker dashboard by its ID, including all tile definitions (charts, tables, text, filters), layout, linked Looks, and underlying queries.2 params▾

Retrieve the full metadata of a Looker dashboard by its ID, including all tile definitions (charts, tables, text, filters), layout, linked Looks, and underlying queries.

NameTypeRequiredDescription

dashboard_idstringrequiredThe ID of the Looker dashboard to retrieve

fieldsstringoptionalComma-separated list of dashboard fields to include in the response

googlelooker_get_look_results#Run a saved Look and return results in the specified format. Executes the Look's underlying query against the connected database. Use result_format to control the output: json for structured data, csv for tabular export, xlsx for Excel.14 params▾

Run a saved Look and return results in the specified format. Executes the Look's underlying query against the connected database. Use result_format to control the output: json for structured data, csv for tabular export, xlsx for Excel.

NameTypeRequiredDescription

look_idstringrequiredThe numeric ID of the Look to fetch results from

result_formatstringrequiredDesired output format for results. Accepted values: json, json_detail, json_bi, csv, txt, html, md, xlsx, sql, png, jpg

apply_formattingbooleanoptionalApply model-specified formatting to each result value

apply_visbooleanoptionalApply visualization options to results

cachebooleanoptionalGet results from cache if available. Set to false to force a fresh database query.

cache_onlybooleanoptionalRetrieve any results from cache even if expired

force_productionbooleanoptionalOverride development mode settings to force use of production models

generate_drill_linksbooleanoptionalGenerate drill links for json_detail format

image_heightintegeroptionalRender height for image formats (png, jpg)

image_widthintegeroptionalRender width for image formats (png, jpg)

limitintegeroptionalMaximum number of rows to return. May override the limit in the saved query.

path_prefixstringoptionalPrefix to use for drill links (URL encoded)

rebuild_pdtsbooleanoptionalRebuild Persistent Derived Tables (PDTs) used in the query

server_table_calcsbooleanoptionalPerform table calculations on query results server-side

googlelooker_list_dashboards#List all dashboards in a Looker instance that the caller has access to. Returns dashboard metadata including ID, title, folder, description, and last updated time.1 param▾

List all dashboards in a Looker instance that the caller has access to. Returns dashboard metadata including ID, title, folder, description, and last updated time.

NameTypeRequiredDescription

fieldsstringoptionalComma-separated list of dashboard fields to include in the response

googlelooker_list_explores#Retrieve a LookML model by name. The response includes an explores array listing all available explores in that model. Use fields=explores to limit the response to just explore metadata.2 params▾

Retrieve a LookML model by name. The response includes an explores array listing all available explores in that model. Use fields=explores to limit the response to just explore metadata.

NameTypeRequiredDescription

model_namestringrequiredThe LookML model name to retrieve explores for

fieldsstringoptionalComma-separated list of model fields to include in the response

googlelooker_list_folders#List all folders (spaces) in the Looker instance including personal folders. Returns folder ID, name, parent folder, creator, and content counts. Use folder IDs to filter Looks and Dashboards by location.1 param▾

List all folders (spaces) in the Looker instance including personal folders. Returns folder ID, name, parent folder, creator, and content counts. Use folder IDs to filter Looks and Dashboards by location.

NameTypeRequiredDescription

fieldsstringoptionalComma-separated list of folder fields to include in the response

googlelooker_list_looks#List all Looks the caller has access to. Returns Look metadata including ID, title, folder, owner, and last run time. Soft-deleted Looks are excluded.4 params▾

List all Looks the caller has access to. Returns Look metadata including ID, title, folder, owner, and last run time. Soft-deleted Looks are excluded.

NameTypeRequiredDescription

fieldsstringoptionalComma-separated list of Look fields to include in the response

limitintegeroptionalMaximum number of Looks to return

offsetintegeroptionalNumber of results to skip before returning any

sortsstringoptionalComma-separated list of fields to sort results by

googlelooker_list_models#List all available LookML models in the Looker instance. Returns each model's name, project, allowed database connections, and explore count. Use this to discover which models and explores are available before running queries.1 param▾

List all available LookML models in the Looker instance. Returns each model's name, project, allowed database connections, and explore count. Use this to discover which models and explores are available before running queries.

NameTypeRequiredDescription

fieldsstringoptionalComma-separated list of model fields to include in the response

googlelooker_run_inline_query#Execute an ad-hoc query against a LookML model and explore without saving it as a Look. Specify fields, filters, sorts, and a row limit. Useful for one-off analysis and agent-driven data exploration. Complex queries may take longer; 120s timeout applied.7 params▾

Execute an ad-hoc query against a LookML model and explore without saving it as a Look. Specify fields, filters, sorts, and a row limit. Useful for one-off analysis and agent-driven data exploration. Complex queries may take longer; 120s timeout applied.

NameTypeRequiredDescription

fieldsstringrequiredComma-separated list of LookML field names to include (e.g., orders.count,orders.total_revenue)

modelstringrequiredThe LookML model name to query against

result_formatstringrequiredOutput format for the query results. Accepted values: json, json_detail, json_bi, csv, txt, html, md, xlsx, sql, png, jpg

viewstringrequiredThe explore (view) name within the model to query

filtersobjectoptionalFilter conditions as a JSON object (field_name: filter_value pairs)

limitintegeroptionalMaximum number of rows to return from the query

sortsstringoptionalComma-separated list of sort fields with optional direction (e.g., orders.total_revenue desc)

googlelooker_run_look#Run a saved Look and return the results in the specified format. Executes the Look's underlying query against the connected database and returns the current data.14 params▾

Run a saved Look and return the results in the specified format. Executes the Look's underlying query against the connected database and returns the current data.

NameTypeRequiredDescription

look_idstringrequiredThe numeric ID of the Look to run

result_formatstringrequiredDesired output format for results. Accepted values: json, json_detail, csv, txt, html, md, xlsx, sql, png, jpg

apply_formattingbooleanoptionalApply model-specified formatting to each result value

apply_visbooleanoptionalApply visualization options to results

cachebooleanoptionalGet results from cache if available. Set to false to force a fresh database query.

cache_onlybooleanoptionalRetrieve any results from cache even if expired

force_productionbooleanoptionalOverride development mode settings to force use of production models

generate_drill_linksbooleanoptionalGenerate drill links for json_detail format

image_heightintegeroptionalRender height for image formats (png, jpg)

image_widthintegeroptionalRender width for image formats (png, jpg)

limitintegeroptionalMaximum number of rows to return. May override the limit in the saved query.

path_prefixstringoptionalPrefix to use for drill links (URL encoded)

rebuild_pdtsbooleanoptionalRebuild Persistent Derived Tables (PDTs) used in the query

server_table_calcsbooleanoptionalPerform table calculations on query results server-side