MCP & AI Agent Integration

Ninox
automation.

13 AI agent actions for Ninox — callable from any MCP-compatible runtime, Claude, Cursor, or Cerebral OS workflow. Use Ninox to organize files, generate documents, and manage permissions programmatically. 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
13
actions
100%
governed
<200ms
latency
13
AI agent actions
9
Read operations
4
Write operations
1
High-risk actions (approval gated)
Files & Documents Ninox 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 Ninox.

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 Database
ninox:get_database
Fetch a single database by ID with metadata and structure information.
Read Low risk
Get File
ninox:get_file
Get file metadata and download URL for a file attachment.
Read Low risk
Get Record
ninox:get_record
Fetch a single record by ID with all field values.
Read Low risk
Get Table
ninox:get_table
Fetch a single table by ID with field definitions and metadata.
Read Low risk
List Databases
ninox:list_databases
List all databases accessible to the authenticated user.
Read Low risk
List Files
ninox:list_files
List all files attached to a specific field in a record.
Read Low risk
List Records
ninox:list_records
List records from a table with optional filtering and sorting.
Read Low risk
List Tables
ninox:list_tables
List all tables in a database with basic metadata.
Read Low risk
Search Records
ninox:search_records
Search records using Ninox query language with advanced filtering.
Read Low risk
Create Record
ninox:create_record
Create a new record in a table with the specified field values.
Write Medium risk
Delete Record
ninox:delete_record
Delete a record permanently. This action cannot be undone.
Write High risk
Execute Script
ninox:execute_script
Execute a Ninox script and return the result.
Write Medium risk
Update Record
ninox:update_record
Update an existing record with new field values.
Write Medium risk
MCP & Runtime API

Call Ninox
from any AI agent.

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

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

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 Ninox data
Call ninox:get_database 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 Ninox
Dry-run validates ninox:create_record 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 Ninox action
governed end-to-end.

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

Ninox works best
alongside these.

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

Ninox integration

Start free.
No credit card required.

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

Start free — 1,000 runs Browse all integrations →