Platform
Platform Overview Maps Memory Shadow Mode Widget Governance Actions Integrations
Developers
Overview Catalog Guardrails Dry Run Idempotency Credentials Audit Trail API Reference
Company
About Blog Contact Book a Demo
MCP Integrations Onedesk
MCP & AI Agent Integration

Onedesk
automation.

16 AI agent actions for Onedesk — callable from any MCP-compatible runtime, Claude, Cursor, or Cerebral OS workflow. Use Onedesk 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.

Connect Onedesk free Browse all integrations →
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
9
Read operations
7
Write operations
0
High-risk actions (approval gated)
Customer Support Onedesk 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 Onedesk.

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 Comments
onedesk:get_comments
Get comments for a ticket in OneDesk.
Read Low risk
Get Organization
onedesk:get_organization
Fetch a single organization by ID with details.
Read Low risk
Get Project
onedesk:get_project
Fetch a single project by ID with details and status.
Read Low risk
Get Ticket
onedesk:get_ticket
Fetch a single ticket by ID with details and status.
Read Low risk
Get User
onedesk:get_user
Fetch a single user by ID with profile details.
Read Low risk
List Organizations
onedesk:list_organizations
List organizations with optional filtering and pagination.
Read Low risk
List Projects
onedesk:list_projects
List projects with optional filtering and pagination.
Read Low risk
List Tickets
onedesk:list_tickets
List tickets with optional filtering and pagination.
Read Low risk
List Users
onedesk:list_users
List users with optional filtering and pagination.
Read Low risk
Add Comment
onedesk:add_comment
Add a comment to a ticket in OneDesk.
Write Medium risk
Close Ticket
onedesk:close_ticket
Close a ticket and optionally add a resolution note.
Write Medium risk
Create Project
onedesk:create_project
Create a new project in OneDesk.
Write Medium risk
Create Ticket
onedesk:create_ticket
Create a new ticket in OneDesk.
Write Medium risk
Create User
onedesk:create_user
Create a new user in OneDesk.
Write Medium risk
Update Project
onedesk:update_project
Update an existing project in OneDesk.
Write Medium risk
Update Ticket
onedesk:update_ticket
Update an existing ticket in OneDesk.
Write Medium risk
MCP & Runtime API

Call Onedesk
from any AI agent.

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

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

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 Onedesk data
Call onedesk:get_comments 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 Onedesk
Dry-run validates onedesk:add_comment 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 Onedesk action
governed end-to-end.

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

Onedesk works best
alongside these.

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

Zendesk Intercom Reamaze Slack Hubspot
Onedesk integration

Start free.
No credit card required.

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

Start free — 1,000 runs Browse all integrations →