Onedesk for AI agents

OneDesk combines help desk and project management in one platform so teams can handle customer tickets and project tasks together. Support and product teams use it to track work in a single system. Connect it once through Arc0, and your agent, or Claude, ChatGPT and Cursor, can use it through one MCP endpoint, limited to what each user approved.

Customer supportAPI keyMCP + RESTonedesk.com
AUDIT LOG · ONEDESKPOLICY: acme-support
09:41:07 · claude · u_8f2read
onedesk.get_issues
Get Issues✓ allowed · 212ms
09:41:08 · claude · u_8f2read
onedesk.get_tickets
Get Tickets✓ allowed · 164ms
09:41:09 · claude · u_8f2write
onedesk.create_worklog
Create Worklog Entry✓ approved · approved by user
09:41:12 · claude · u_8f2destructive
onedesk.delete_task
Delete Task✕ blocked · policy: deny
EVERY ONEDESK CALL, ON THE RECORD
01 · USE CASES

What agents do in Onedesk.

01

Log a worklog entry on a ticket

Record time spent on a support ticket or task so billing and reporting stay accurate.

02

Check open tickets read-only

Pull the list of open tickets to see what is waiting before triaging new requests.

03

Delete a ticket with approval

Remove a duplicate or spam ticket only after a support lead confirms it should be closed for good.

02 · ACTIONS

24 Onedesk actions, graded by risk.

Every Onedesk action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.

read

13

Look things up. Allowed by default.

  • onedesk.get_issues
    Get Issues
  • onedesk.get_tickets
    Get Tickets
  • onedesk.get_comments
    Get Comments
  • onedesk.get_feedback
    Get Feedback Items
  • onedesk.get_messages
    Get Messages
  • onedesk.get_worklogs
    Get Worklogs
  • onedesk.get_attachments
    Get Attachments
  • onedesk.get_requirements
    Get Requirements
  • onedesk.get_task_details
    Get Task Details
  • onedesk.get_issue_details
    Get Issue Details
  • onedesk.get_comment_details
    Get Comment Details
  • onedesk.get_feedback_details
    Get Feedback Details
  • onedesk.get_timesheet_details
    Get Timesheet Details

write

1

Create and change things. Allow, or ask the user first.

  • onedesk.create_worklog
    Create Worklog Entry

destructive

10

Delete, cancel or archive. Ask first, or deny outright.

  • onedesk.delete_task
    Delete Task
  • onedesk.delete_user
    Delete User
  • onedesk.delete_ticket
    Delete Ticket
  • onedesk.delete_comment
    Delete Comment
  • onedesk.delete_message
    Delete Message
  • onedesk.delete_project
    Delete Project
  • onedesk.delete_customer
    Delete Customer
  • onedesk.delete_timesheet
    Delete Timesheet
  • onedesk.delete_attachment
    Delete Attachment
  • onedesk.delete_requirement
    Delete Requirement
03 · HOW IT WORKS

Onedesk in three steps.

  1. 01Your users connect OnedeskThey add their Onedesk api key on Arc0 Connect, under your brand. It goes straight into the vault.
  2. 02You set the rulesReads run, writes like “create Worklog Entry” can wait for the user, and “delete Task” can be denied outright.
  3. 03Any agent can actYour agent calls Onedesk through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
POLICY.TS
await arc0.policies.set('onedesk', {
  read: 'allow',
  write: 'ask',        // create_worklog
  destructive: 'deny',  // delete_task
})

# Claude Code: the same connection, one URL
$ claude mcp add --transport http arc0 \
    https://mcp.arc0.ai/u/u_8f2
04 · AUTH AND DATA

How Onedesk connects.

Users add their Onedesk api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.

The same Onedesk connection serves your agent over MCP and your own backend over REST and the proxy, so a user connects once. How Arc0 handles credentials →

AUTH
API key
CREDENTIALS
Per-tenant encrypted vault
MODEL SEES
Results only, never credentials
AUDIT LOG
Every call, on every plan
05 · WORKS WITH

Use Onedesk from any agent.

Claude
ChatGPT
Cursor
Codex
VS Code
OpenAI Agents SDK
Claude Agent SDK
Vercel AI SDK
Mastra
LangGraph
07 · FAQ

Onedesk and Arc0, answered.

Q01

Can I use Onedesk with Claude, ChatGPT or Cursor?

Yes. Connect Onedesk to Arc0 once, then add your Arc0 MCP URL to Claude, ChatGPT, Cursor, Claude Code or any other remote-MCP client. Each assistant only gets the Onedesk actions you allow.

Q02

How do users connect Onedesk?

Users add their Onedesk api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.

Q03

Which Onedesk actions can my agent take?

24 in total: 13 read, 1 write and 10 destructive, such as “create Worklog Entry”. Your policies decide which of them each agent may call.

Q04

Can I stop my agent from deleting things in Onedesk?

Yes. Actions like “delete Task” are graded destructive. Set destructive actions to deny, or to ask so the user approves each one, and blocked calls still show up on the audit log.

Q05

Can my own backend call Onedesk too?

Yes. The same Onedesk connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.

Get started

Plug Onedesk into your agent.

Your users connect Onedesk once, under your brand. Your agent gets 24 actions behind your policies, with every call on the record.

Free to build · MCP + REST · Audit log on every plan