MCP & AI Agent Integration

Confection
automation.

13 AI agent actions for Confection — callable from any MCP-compatible runtime, Claude, Cursor, or Cerebral OS workflow. Use Confection to manage subscribers, trigger campaigns, and personalize outreach at scale. 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
6
Read operations
7
Write operations
0
High-risk actions (approval gated)
Marketing Confection is a Marketing integration — use it to automate email campaigns, audience management, and automation from any AI agent or MCP-compatible runtime.
Actions

What you can do
with Confection.

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 Campaign
confection:get_campaign
Fetch a single marketing campaign by ID with its details and performance metrics.
Read Low risk
Get Customer
confection:get_customer
Fetch a single customer by ID with their profile, points balance, and tier status.
Read Low risk
Get Points History
confection:get_points_history
Get a customer's points transaction history with optional filtering by type and date range.
Read Low risk
List Campaigns
confection:list_campaigns
List marketing campaigns with optional filtering by status, type, and date range.
Read Low risk
List Customers
confection:list_customers
List customers with optional filtering by email, tier, status, or points balance.
Read Low risk
List Rewards
confection:list_rewards
List available rewards that customers can redeem with their points.
Read Low risk
Award Points
confection:award_points
Award points to a customer for various activities like purchases, referrals, or bonuses.
Write Medium risk
Create Customer
confection:create_customer
Create a new customer in the loyalty program with optional initial points.
Write Medium risk
Create Reward
confection:create_reward
Create a new reward that customers can redeem with their points.
Write Medium risk
Redeem Points
confection:redeem_points
Redeem points from a customer's account for rewards, discounts, or other benefits.
Write Medium risk
Redeem Reward
confection:redeem_reward
Redeem a specific reward for a customer, deducting the required points from their balance.
Write Medium risk
Send Notification
confection:send_notification
Send a notification (email, SMS, or push) to a customer with optional template and scheduling.
Write Medium risk
Update Customer
confection:update_customer
Update an existing customer's profile information and status.
Write Medium risk
MCP & Runtime API

Call Confection
from any AI agent.

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

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

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 Confection data
Call confection:get_campaign 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 Confection
Dry-run validates confection:award_points before execution
Approval gate fires if risk level is high
Action executes with full governance — logged, audited, reversible
Trigger
Campaign or subscriber event
Segment audience
Trigger follow-up
Log metrics to dashboard
How it works

Every Confection action
governed end-to-end.

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

Confection works best
alongside these.

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

Confection integration

Start free.
No credit card required.

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

Start free — 1,000 runs Browse all integrations →