Platform
Platform Overview Maps Memory Shadow Mode Widget Governance Actions Integrations
Developers
Overview Catalog Guardrails Dry Run Idempotency Credentials Audit Trail API Reference
Company
About Blog Contact Book a Demo
MCP Integrations Keboola
MCP & AI Agent Integration

Keboola
automation.

16 AI agent actions for Keboola — callable from any MCP-compatible runtime, Claude, Cursor, or Cerebral OS workflow. Use Keboola to automate business processes and connect tools in your stack. Full governance, audit trail, and dry-run safety on every execution.

Connect Keboola free Browse all integrations →
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
10
Read operations
6
Write operations
2
High-risk actions (approval gated)
Business Tools Keboola is a Business Tools integration — use it to automate business operations and workflow automation from any AI agent or MCP-compatible runtime.
Actions

What you can do
with Keboola.

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 Bucket
keboola:get_bucket
Fetch a single storage bucket with its configuration and metadata.
Read Low risk
Get Configuration
keboola:get_configuration
Fetch a single component configuration with its settings and parameters.
Read Low risk
Get Job
keboola:get_job
Fetch a single job with its status, results, and execution details.
Read Low risk
Get Orchestration
keboola:get_orchestration
Fetch a single orchestration with its configuration and task details.
Read Low risk
Get Table
keboola:get_table
Fetch a single table with its metadata, columns, and configuration.
Read Low risk
List Buckets
keboola:list_buckets
List all storage buckets with optional filtering by stage.
Read Low risk
List Configurations
keboola:list_configurations
List all configurations for a specific component.
Read Low risk
List Jobs
keboola:list_jobs
List jobs with optional filtering by status, component, and pagination.
Read Low risk
List Orchestrations
keboola:list_orchestrations
List all orchestrations in the project.
Read Low risk
List Tables
keboola:list_tables
List all tables with optional filtering by bucket.
Read Low risk
Create Bucket
keboola:create_bucket
Create a new storage bucket in the specified stage.
Write Medium risk
Create Table
keboola:create_table
Create a new table in a storage bucket, optionally with initial data.
Write Medium risk
Delete Bucket
keboola:delete_bucket
Delete a storage bucket. WARNING: This permanently removes the bucket and all its data.
Write High risk
Delete Table
keboola:delete_table
Delete a table. WARNING: This permanently removes the table and all its data.
Write High risk
Run Component
keboola:run_component
Execute a component with specified configuration. Returns job details for tracking.
Write Medium risk
Run Orchestration
keboola:run_orchestration
Execute an orchestration. Returns job details for tracking the orchestration run.
Write Medium risk
MCP & Runtime API

Call Keboola
from any AI agent.

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

keboola:get_bucket READ
# Call via Runtime API
curl
-X POST \
  "https://api.cerebralos.com/v1/runtime/actions/run"
  -H "X-API-Key: YOUR_KEY" \
  -d '{
    "verb": "keboola:get_bucket",
    "args": {},
    "execution_id": "agent-001"
  }'
keboola:create_bucket 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": "keboola:create_bucket",
    "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 Keboola.

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 Keboola data
Call keboola:get_bucket 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 Keboola
Dry-run validates keboola:create_bucket before execution
Approval gate fires if risk level is high
Action executes with full governance — logged, audited, reversible
Trigger
Event in Keboola
Process with AI agent
Take governed action
Log to audit trail
How it works

Every Keboola action
governed end-to-end.

Cerebral OS isn't a connector. It's the execution layer that sits in front of Keboola — 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 Keboola action before it touches production. See exactly what would happen before a single real call is made.
Immutable audit trail
Every Keboola action is logged — what ran, what changed, who approved it, when it happened. Full history on every verb, forever.
Connect with

Keboola works best
alongside these.

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

Slack Gmail Hubspot Google Sheets Notion
Keboola integration

Start free.
No credit card required.

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

Start free — 1,000 runs Browse all integrations →