Request Tracker (RT) for AI agents
Request Tracker (RT) is an open-source ticketing system for managing support requests, queues, assets, and knowledge articles across a help desk. 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.
What agents do in Request Tracker (RT).
Search open tickets
Search tickets in a queue to find ones still waiting on a customer response.
Reply to a ticket
Reply to a ticket with an update once the underlying issue is resolved.
Check history before closing
Get a ticket's full history first, then update its status only after confirming nothing is outstanding.
11 Request Tracker (RT) actions, graded by risk.
Every Request Tracker (RT) action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
7Look things up. Allowed by default.
- request_tracker_rt.get_queueGet Queue
- request_tracker_rt.get_ticketGet Ticket
- request_tracker_rt.list_queuesList Queues
- request_tracker_rt.search_usersSearch Users
- request_tracker_rt.search_ticketsSearch Tickets
- request_tracker_rt.get_ticket_historyGet Ticket History
- request_tracker_rt.list_ticket_attachmentsList Ticket Attachments
write
4Create and change things. Allow, or ask the user first.
- request_tracker_rt.create_ticketCreate Ticket
- request_tracker_rt.update_ticketUpdate Ticket
- request_tracker_rt.add_ticket_commentAdd Ticket Comment
- request_tracker_rt.reply_to_ticketReply to Ticket
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
Request Tracker (RT) in three steps.
- 01Your users connect Request Tracker (RT)They add their Request Tracker (RT) api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, and writes like “create Ticket” can wait for the user to approve.
- 03Any agent can actYour agent calls Request Tracker (RT) through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('request_tracker_rt', { read: 'allow', write: 'ask', // create_ticket destructive: 'deny', }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Request Tracker (RT) connects.
Users add their Request Tracker (RT) 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 Request Tracker (RT) 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
Use Request Tracker (RT) from any agent.
Request Tracker (RT) and Arc0, answered.
Can I use Request Tracker (RT) with Claude, ChatGPT or Cursor?
Yes. Connect Request Tracker (RT) 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 Request Tracker (RT) actions you allow.
How do users connect Request Tracker (RT)?
Users add their Request Tracker (RT) 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.
Which Request Tracker (RT) actions can my agent take?
11 in total: 7 read, 4 write and 0 destructive, such as “create Ticket”. Your policies decide which of them each agent may call.
Can I make my agent read-only in Request Tracker (RT)?
Yes. Allow read actions and deny writes in the Request Tracker (RT) policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call Request Tracker (RT) too?
Yes. The same Request Tracker (RT) connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Request Tracker (RT) into your agent.
Your users connect Request Tracker (RT) once, under your brand. Your agent gets 11 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan