MCP & AI Agent Integration

Softr
automation.

14 AI agent actions for Softr — callable from any MCP-compatible runtime, Claude, Cursor, or Cerebral OS workflow. Use Softr to send alerts, post updates, and coordinate team actions based on triggers. 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
14
actions
100%
governed
<200ms
latency
14
AI agent actions
6
Read operations
8
Write operations
2
High-risk actions (approval gated)
Communication Softr is a Communication integration — use it to automate messaging, notifications, and team collaboration from any AI agent or MCP-compatible runtime.
Actions

What you can do
with Softr.

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 App
softr:get_app
Fetch details of a specific Softr application including name, domain, and status.
Read Low risk
Get Record
softr:get_record
Fetch a specific record from a Softr application's data source.
Read Low risk
Get User
softr:get_user
Fetch details of a specific user in a Softr application.
Read Low risk
List Apps
softr:list_apps
List all Softr applications in your account with optional filtering.
Read Low risk
List Records
softr:list_records
List records from a Softr application's data source with filtering and sorting.
Read Low risk
List Users
softr:list_users
List users in a Softr application with optional filtering and search.
Read Low risk
Create Record
softr:create_record
Create a new record in a Softr application's data source.
Write Medium risk
Create User
softr:create_user
Create a new user in a Softr application.
Write Medium risk
Delete Record
softr:delete_record
Delete a record from a Softr application's data source. This action cannot be undone.
Write High risk
Delete User
softr:delete_user
Delete a user from a Softr application. This action cannot be undone.
Write High risk
Publish App
softr:publish_app
Publish a Softr application to make it live and accessible to users.
Write Medium risk
Send Notification
softr:send_notification
Send an in-app notification to a specific user in a Softr application.
Write Medium risk
Update Record
softr:update_record
Update an existing record in a Softr application's data source.
Write Medium risk
Update User
softr:update_user
Update an existing user in a Softr application.
Write Medium risk
MCP & Runtime API

Call Softr
from any AI agent.

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

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

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 Softr data
Call softr:get_app 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 Softr
Dry-run validates softr:create_record before execution
Approval gate fires if risk level is high
Action executes with full governance — logged, audited, reversible
Trigger
Message or alert triggered
Route to right channel
Notify relevant team
Log to audit trail
How it works

Every Softr action
governed end-to-end.

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

Softr works best
alongside these.

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

Softr integration

Start free.
No credit card required.

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

Start free — 1,000 runs Browse all integrations →