MCP & AI Agent Integration

Re:amaze
automation.

16 AI agent actions for Re:amaze — callable from any MCP-compatible runtime, Claude, Cursor, or Cerebral OS workflow. Use Re:amaze to resolve tickets, route conversations, and escalate edge cases without a human in the loop. 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
16
actions
100%
governed
<200ms
latency
16
AI agent actions
6
Read operations
10
Write operations
0
High-risk actions (approval gated)
Customer Support Re:amaze is a Customer Support integration — use it to automate ticket management, conversations, and escalations from any AI agent or MCP-compatible runtime.
Actions

What you can do
with Re:amaze.

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 Articles
reamaze:get_articles
Retrieve knowledge base articles from Re:amaze. Use this to search help documentation, FAQs, and support articles. Useful for AI to reference when answering customer questions.
Read Low risk
Get Conversation
reamaze:get_conversation
Execute get_conversation action via reamaze
Read Low risk
Get Conversations
reamaze:get_conversations
Get conversations from Re:amaze with filtering and sorting. Common use cases: (1) Get oldest conversation waiting for response: {filter: "open", tag: "assigned-to-ben", sort: "updated", page_size: 10} then take LAST item in conversations array. (2) Get all open unassigned tickets: {filter: "unassigned"}. (3) Get all conversations for a customer: {for: "customer@example.com"}. Note: sort: "updated" returns NEWEST FIRST, so oldest conversation is at END of array.
Read Low risk
Get Customer
reamaze:get_customer
Execute get_customer action via reamaze
Read Low risk
Get Macros
reamaze:get_macros
Execute get_macros action via reamaze
Read Low risk
Search Conversations
reamaze:search_conversations
Execute search_conversations action via reamaze
Read Low risk
Add Note
reamaze:add_note
Add an internal staff note to a conversation (customers cannot see these notes). This is a convenience wrapper for creating a message with visibility=1 (internal). Use this for staff communication, NOT for customer-facing replies.
Write Low risk
Apply Macro
reamaze:apply_macro
Apply a canned response/macro/template to a conversation with variable substitution. Re:amaze calls these "Response Templates" - this is the standard macro/canned response system. IMPORTANT: Provide EITHER template_id OR template_name (not both). template_id is more efficient. Variables like {{customer_name}} and {{order_id}} are automatically replaced with values from props.variables. Returns the customized message body that was sent to the conversation.
Write Medium risk
Assign Conversation
reamaze:assign_conversation
Assign a conversation to a specific staff member. This is a convenience wrapper for updating conversation with assignee field. CRITICAL: Use this to escalate tickets to humans when AI cannot complete the task.
Write Low risk
Create Contact Note
reamaze:create_contact_note
Add a staff note to a customer's contact profile (not to a specific conversation). These notes are visible to all staff members when viewing the customer's profile. Use this for permanent customer information that should persist across all conversations.
Write Low risk
Create Conversation
reamaze:create_conversation
Create a new Re:amaze conversation/ticket on behalf of a customer. This is useful for creating tickets from custom forms, API integrations, or automated systems. The conversation will appear as if the customer initiated it.
Write Medium risk
Create Message
reamaze:create_message
Create a new message (reply) in an existing Re:amaze conversation. CRITICAL: This is the primary way for AI to respond to customer tickets. Use visibility='public' for customer-facing replies, visibility='internal' for staff notes.
Write Medium risk
Merge Contact
reamaze:merge_contact
Merge duplicate customer profiles
Write Medium risk
Set Reminder
reamaze:set_reminder
Execute set_reminder action via reamaze
Write Low risk
Update Contact
reamaze:update_contact
Execute update_contact action via reamaze
Write Low risk
Update Conversation
reamaze:update_conversation
Update a Re:amaze conversation/ticket. Use this to assign tickets, change status, or update tags. CRITICAL: When cerebral cannot complete a task, use assignee_email to escalate to a human. Only provide fields you want to change - others remain unchanged.
Write Low risk
MCP & Runtime API

Call Re:amaze
from any AI agent.

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

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

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 Re:amaze data
Call reamaze:get_articles 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 Re:amaze
Dry-run validates reamaze:add_note before execution
Approval gate fires if risk level is high
Action executes with full governance — logged, audited, reversible
Trigger
Support ticket created
Classify with AI
Auto-resolve or escalate
Notify team with full context
How it works

Every Re:amaze action
governed end-to-end.

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

Re:amaze works best
alongside these.

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

Re:amaze integration

Start free.
No credit card required.

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

Start free — 1,000 runs Browse all integrations →