MCP & AI Agent Integration

Metabase
automation.

16 AI agent actions for Metabase — callable from any MCP-compatible runtime, Claude, Cursor, or Cerebral OS workflow. Use Metabase to create tasks, update project status, and coordinate work across teams automatically. Full governance, audit trail, and dry-run safety on every execution.

No credit card required
Live in production environments
<200ms median execution
Dry-run before production
Execution trace
live
16
actions
100%
governed
<200ms
latency
16
AI agent actions
8
Read operations
8
Write operations
2
High-risk actions (approval gated)
Productivity Metabase is a Productivity integration — use it to automate tasks, projects, and team workflows from any AI agent or MCP-compatible runtime.
Actions

What you can do
with Metabase.

Every action below is available as an MCP tool and a verb in Cerebral OS — callable from any AI agent, Claude, Cursor, Windsurf, or your own runtime via the BYOA API. All executions are governed, audited, and dry-run safe.

Get Card
metabase:get_card
Fetch a single card (question) by ID with its query and visualization settings.
Read Low risk
Get Collection
metabase:get_collection
Fetch a single collection by ID with its items.
Read Low risk
Get Dashboard
metabase:get_dashboard
Fetch a single dashboard by ID with its cards and layout information.
Read Low risk
Get Database
metabase:get_database
Fetch a single database by ID with optional table information.
Read Low risk
List Cards
metabase:list_cards
List all accessible cards (questions) with optional filtering.
Read Low risk
List Collections
metabase:list_collections
List all accessible collections.
Read Low risk
List Dashboards
metabase:list_dashboards
List all accessible dashboards with optional filtering by collection.
Read Low risk
List Databases
metabase:list_databases
List all accessible databases in Metabase.
Read Low risk
Create Card
metabase:create_card
Create a new card (question) in Metabase.
Write Medium risk
Create Collection
metabase:create_collection
Create a new collection in Metabase.
Write Medium risk
Create Dashboard
metabase:create_dashboard
Create a new dashboard in Metabase.
Write Medium risk
Delete Card
metabase:delete_card
Delete a card (question) from Metabase. This action cannot be undone.
Write High risk
Delete Dashboard
metabase:delete_dashboard
Delete a dashboard from Metabase. This action cannot be undone.
Write High risk
Run Query
metabase:run_query
Execute a query for a specific card and return the results.
Write Medium risk
Update Card
metabase:update_card
Update an existing card (question) in Metabase.
Write Medium risk
Update Dashboard
metabase:update_dashboard
Update an existing dashboard in Metabase.
Write Medium risk
MCP & Runtime API

Call Metabase
from any AI agent.

Any AI agent — Claude, Cursor, LangChain, AutoGen, or your own — can call Metabase actions through the Cerebral OS Runtime API. Governance, credentials, and audit trail fire automatically.

metabase:get_card READ
# Call via Runtime API
curl
-X POST \
  "https://api.cerebralos.com/v1/runtime/actions/run"
  -H "X-API-Key: YOUR_KEY" \
  -d '{
    "verb": "metabase:get_card",
    "args": {},
    "execution_id": "agent-001"
  }'
metabase:create_card WRITE
# Dry-run first — no production risk
curl
-X POST \
  "https://api.cerebralos.com/v1/runtime/actions/run"
  -H "X-API-Key: YOUR_KEY" \
  -d '{
    "verb": "metabase:create_card",
    "args": {},
    "execution_id": "agent-001",
    "metadata": {"dryRun": true}
  }'
Get your Runtime API key at app.cerebralos.com/signup — 1,000 free executions, no credit card required.
AI agent examples

What your AI agent
can do with Metabase.

Real patterns your AI agent can execute via MCP or the Runtime API. Every action governed, dry-run safe, and fully audited.

Trigger
AI agent needs Metabase data
Call metabase:get_card via MCP or Runtime API
AI processes result and takes next action
Full execution logged to audit trail automatically
Trigger
Workflow needs to write to Metabase
Dry-run validates metabase:create_card before execution
Approval gate fires if risk level is high
Action executes with full governance — logged, audited, reversible
Trigger
Task or project event
Update status automatically
Notify assignees
Sync across tools
How it works

Every Metabase action
governed end-to-end.

Cerebral OS isn't a connector. It's the execution layer that sits in front of Metabase — adding governance, dry-run safety, and a full audit trail to every operation.

Governance first
Every verb carries a risk classification. High-risk writes require explicit approval gates before they execute in production.
Dry-run safe
Simulate any Metabase action before it touches production. See exactly what would happen before a single real call is made.
Immutable audit trail
Every Metabase action is logged — what ran, what changed, who approved it, when it happened. Full history on every verb, forever.
Connect with

Metabase works best
alongside these.

Build multi-step workflows that connect Metabase to the rest of your stack. All governed. All audited.

Metabase integration

Start free.
No credit card required.

Start free with 1,000 runs — no credit card required. Connect Metabase in minutes, dry-run every action before it touches production, full audit trail on everything.

Start free — 1,000 runs Browse all integrations →