MCP & AI Agent Integration

Dbt
automation.

18 AI agent actions for Dbt — callable from any MCP-compatible runtime, Claude, Cursor, or Cerebral OS workflow. Use Dbt 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
18
actions
100%
governed
<200ms
latency
18
AI agent actions
12
Read operations
6
Write operations
2
High-risk actions (approval gated)
Productivity Dbt 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 Dbt.

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 Account
dbt:get_account
Fetch details for a specific dbt Cloud account.
Read Low risk
Get Connection
dbt:get_connection
Fetch details for a specific dbt Cloud connection.
Read Low risk
Get Environment
dbt:get_environment
Fetch details for a specific dbt Cloud environment.
Read Low risk
Get Job
dbt:get_job
Fetch details for a specific dbt Cloud job.
Read Low risk
Get Project
dbt:get_project
Fetch details for a specific dbt Cloud project.
Read Low risk
Get Run
dbt:get_run
Fetch details for a specific dbt Cloud run.
Read Low risk
Get Run Artifact
dbt:get_run_artifact
Fetch a specific artifact from a dbt Cloud run.
Read Low risk
List Connections
dbt:list_connections
List all connections in the dbt Cloud account with optional project filtering.
Read Low risk
List Environments
dbt:list_environments
List all environments in the dbt Cloud account with optional project filtering.
Read Low risk
List Jobs
dbt:list_jobs
List all jobs in the dbt Cloud account with optional project filtering.
Read Low risk
List Projects
dbt:list_projects
List all projects in the dbt Cloud account with pagination support.
Read Low risk
List Runs
dbt:list_runs
List job runs in the dbt Cloud account with optional job filtering.
Read Low risk
Cancel Run
dbt:cancel_run
Cancel a running or queued dbt Cloud job run.
Write High risk
Create Project
dbt:create_project
Create a new dbt Cloud project.
Write Medium risk
Delete Project
dbt:delete_project
Delete a dbt Cloud project permanently. This action cannot be undone.
Write High risk
Test Connection
dbt:test_connection
Test a dbt Cloud connection to verify it can connect to the data warehouse.
Write Medium risk
Trigger Job
dbt:trigger_job
Trigger a dbt Cloud job to run immediately.
Write Medium risk
Update Project
dbt:update_project
Update an existing dbt Cloud project.
Write Medium risk
MCP & Runtime API

Call Dbt
from any AI agent.

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

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

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 Dbt data
Call dbt:get_account 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 Dbt
Dry-run validates dbt:cancel_run 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 Dbt action
governed end-to-end.

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

Dbt works best
alongside these.

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

Dbt integration

Start free.
No credit card required.

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

Start free — 1,000 runs Browse all integrations →