Integration

Looker integration

Looker is a cloud-based business intelligence and data analytics platform from Google Cloud. The Looker API 4.0 lets you authenticate with API3 credentials, run queries against LookML models, list and execute saved Looks and Dashboards (with optional binary export to CSV/PNG/XLSX), search content, manage users, folders and scheduled plans. Essential for BI automation, embedded analytics, and reporting pipelines.

Connect Looker How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in Looker.Built from the 21 Looker tools below, on the connection you add once.

Common Looker use cases

content audit
ad-hoc analytics
BI exploration
BI metadata
permissions audit
user audit
data export
user lookup
user details
verify token

What you can do with Looker

Each of these is one operation on one endpoint, available both as a workflow step and as a tool an AI agent can call on its own. Nothing bundles several operations into one action, so what a run did stays readable afterwards.

Most endpoints run on the free plan. A few, mainly the ones that publish on your behalf, need a paid plan.

Look, 4 operations

all_looksAll looksGETLists every Look the authenticated user can see.
get_lookGet lookGETRetrieves a single Look by ID with its underlying query_id.
run_lookRun lookGETRuns a saved Look and stores the result (CSV, PNG, XLSX, JSON, etc.) as a file.
search_looksSearch looksGETSearches looks by title, owner, folder, or other attributes.

User, 4 operations

all_usersAll usersGETLists all Looker users with id, name, email, and disabled flag.
get_userGet userGETRetrieves a single Looker user by ID.
meMeGETRetrieves the user record for the currently authenticated API caller.
search_usersSearch usersGETSearches Looker users by name, email, or other attributes.

Dashboard, 3 operations

all_dashboardsAll dashboardsGETLists every dashboard (user-defined and LookML) on the instance.
get_dashboardGet dashboardGETRetrieves a single dashboard with its tiles and filter widgets.
search_dashboardsSearch dashboardsGETSearches dashboards by title, folder, owner, view count, and other filters.

Query, 3 operations

create_queryCreate queryPOSTCreates a Looker query definition (model + view + fields + filters) and returns its id.
run_inline_queryRun inline queryPOSTRuns a one-shot inline query (model + view + fields + filters) without saving it.
run_queryRun queryGETRuns an existing Looker query by id and stores the result file (CSV, PNG, XLSX, JSON, ...).

Lookml model, 2 operations

all_lookml_modelsAll lookml modelsGETLists every LookML model on the instance with its explores.
get_lookml_modelGet lookml modelGETRetrieves a single LookML model and its explores.

Scheduled plan, 2 operations

all_scheduled_plansAll scheduled plansGETLists scheduled plans (recurring email/webhook deliveries of content).
create_scheduled_planCreate scheduled planPOSTCreates a new recurring scheduled delivery for a Look or Dashboard.

Auth, 1 operation

loginLoginPOSTAuthenticates with API3 client_id/client_secret and returns a short-lived access_token.

Content, 1 operation

search_foldersSearch foldersGETFull-text search across folders by name or attributes.

Folder, 1 operation

all_foldersAll foldersGETLists all content folders with their hierarchy.

Looker API rate limits

Looker enforces per-instance and per-endpoint rate limits; access_token expires (default 1 hour, configurable per instance).

These are the limits Looker documents, not ones LiveContext measured. They can change and often depend on your plan, so check the Looker documentation for current values.

Use Looker from Claude Code, Cursor or Codex

Connect Looker in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its Looker operations become tools the client can call, next to every other integration you connected.

Claude Code

claude mcp add --transport http livecontext https://livecontext.ai/mcp --header "X-API-Key: YOUR_API_KEY"

Codex (~/.codex/config.toml)

[mcp_servers.livecontext]
url = "https://livecontext.ai/mcp"

[mcp_servers.livecontext.http_headers]
"X-API-Key" = "YOUR_API_KEY"

Cursor, Claude Desktop and other JSON configs

{
  "mcpServers": {
    "livecontext": {
      "type": "http",
      "url": "https://livecontext.ai/mcp",
      "headers": {
        "X-API-Key": "YOUR_API_KEY"
      }
    }
  }
}

Set up the MCP server step by step

How to connect Looker

Create your workspace
Sign up free. Nothing to install.
Connect Looker once
Add your Looker connection in Settings. Every tool from this integration reuses it, and secrets are encrypted at rest and visible only to you.
Describe the job in chat
The workflow builds itself in front of you and picks the endpoints it needs. Drag the steps yourself on the canvas whenever you would rather be explicit.

Looker integration FAQ

What can you do with the Looker integration?

LiveContext exposes 21 operations on Looker, covering look, user, dashboard and query. Common uses include content audit, ad-hoc analytics and BI exploration.

What are the Looker API rate limits?

Looker enforces per-instance and per-endpoint rate limits; access_token expires (default 1 hour, configurable per instance). Limits are set by Looker and can depend on your plan.