MCP & AI Agent Integration

Plain
automation.

16 AI agent actions for Plain — callable from any MCP-compatible runtime, Claude, Cursor, or Cerebral OS workflow. Use Plain to automate business processes and connect tools in your stack. 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
7
Read operations
9
Write operations
1
High-risk actions (approval gated)
Business Tools Plain is a Business Tools integration — use it to automate business operations and workflow automation from any AI agent or MCP-compatible runtime.
Actions

What you can do
with Plain.

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 Customer
plain:get_customer
Fetch a single customer by ID with their basic information and metadata.
Read Low risk
Get Thread
plain:get_thread
Fetch a single thread (conversation) by ID with its details and status.
Read Low risk
List Customers
plain:list_customers
List customers with optional filtering and pagination.
Read Low risk
List Labels
plain:list_labels
List all available labels that can be applied to threads.
Read Low risk
List Threads
plain:list_threads
List threads with optional filtering and pagination.
Read Low risk
List Timeline Entries
plain:list_timeline_entries
List timeline entries (messages, notes, etc.) from a thread.
Read Low risk
List Users
plain:list_users
List team members/users who can be assigned to threads.
Read Low risk
Add Labels To Thread
plain:add_labels_to_thread
Add labels to a thread (existing labels are preserved).
Write Medium risk
Assign Thread
plain:assign_thread
Assign a thread to a team member or unassign it.
Write Medium risk
Change Thread Status
plain:change_thread_status
Change the status of a thread (mark as todo, snoozed, or done).
Write Medium risk
Create Customer
plain:create_customer
Create a new customer in Plain.
Write Medium risk
Create Thread
plain:create_thread
Create a new thread (conversation) in Plain.
Write Medium risk
Create Timeline Entry
plain:create_timeline_entry
Create a new timeline entry (message, note, etc.) in a thread.
Write Medium risk
Remove Labels From Thread
plain:remove_labels_from_thread
Remove labels from a thread.
Write High risk
Update Customer
plain:update_customer
Update an existing customer in Plain.
Write Medium risk
Update Thread
plain:update_thread
Update an existing thread in Plain.
Write Medium risk
MCP & Runtime API

Call Plain
from any AI agent.

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

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

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 Plain data
Call plain:get_customer 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 Plain
Dry-run validates plain:add_labels_to_thread before execution
Approval gate fires if risk level is high
Action executes with full governance — logged, audited, reversible
Trigger
Event in Plain
Process with AI agent
Take governed action
Log to audit trail
How it works

Every Plain action
governed end-to-end.

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

Plain works best
alongside these.

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

Plain integration

Start free.
No credit card required.

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

Start free — 1,000 runs Browse all integrations →