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 Sanity
MCP & AI Agent Integration

Sanity
automation.

12 AI agent actions for Sanity — callable from any MCP-compatible runtime, Claude, Cursor, or Cerebral OS workflow. Use Sanity to organize files, generate documents, and manage permissions programmatically. Full governance, audit trail, and dry-run safety on every execution.

Connect Sanity free Browse all integrations →
No credit card required
Live in production environments
<200ms median execution
Dry-run before production
Execution trace
live
12
actions
100%
governed
<200ms
latency
12
AI agent actions
4
Read operations
8
Write operations
2
High-risk actions (approval gated)
Files & Documents Sanity is a Files & Documents integration — use it to automate file storage, sharing, and document management from any AI agent or MCP-compatible runtime.
Actions

What you can do
with Sanity.

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 Asset
sanity:get_asset
Fetch asset metadata and URL by asset ID.
Read Low risk
Get Document
sanity:get_document
Fetch a single document by ID from the Sanity dataset.
Read Low risk
List Assets
sanity:list_assets
List assets (images and files) from the Sanity dataset.
Read Low risk
List Documents
sanity:list_documents
List documents from the Sanity dataset using GROQ queries.
Read Low risk
Create Document
sanity:create_document
Create a new document in the Sanity dataset.
Write Medium risk
Delete Asset
sanity:delete_asset
Permanently delete an asset from the Sanity dataset.
Write High risk
Delete Document
sanity:delete_document
Permanently delete a document from the Sanity dataset.
Write High risk
Execute Groq
sanity:execute_groq
Execute a custom GROQ query against the Sanity dataset.
Write Low risk
Publish Document
sanity:publish_document
Publish a draft document by copying it to the published version.
Write Medium risk
Unpublish Document
sanity:unpublish_document
Unpublish a document by converting it to a draft and removing the published version.
Write Medium risk
Update Document
sanity:update_document
Update an existing document in the Sanity dataset using patch operations.
Write Medium risk
Upload Asset
sanity:upload_asset
Upload a file or image asset to Sanity.
Write Medium risk
MCP & Runtime API

Call Sanity
from any AI agent.

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

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

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 Sanity data
Call sanity:get_asset 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 Sanity
Dry-run validates sanity:create_document before execution
Approval gate fires if risk level is high
Action executes with full governance — logged, audited, reversible
Trigger
File or document event
Process with AI
Route for approval
Notify team
How it works

Every Sanity action
governed end-to-end.

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

Sanity works best
alongside these.

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

Google Drive Dropbox Box Notion Slack
Sanity integration

Start free.
No credit card required.

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

Start free — 1,000 runs Browse all integrations →