CarsXE for AI agents
CarsXE provides vehicle data lookups, covering VIN specs, recalls, market value, and history, for teams that need to verify a car before a deal. 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 CarsXE.
Decode a VIN's specifications
Look up a vehicle's specifications from its VIN before listing it or quoting a price.
Check for open recalls
Check whether a vehicle has any open safety recalls before recommending a purchase.
Check lien and theft records
Check a vehicle's lien and theft history before a buyer commits to a sale.
12 CarsXE actions, graded by risk.
Every CarsXE action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
8Look things up. Allowed by default.
- carsxe.get_market_valueGet Vehicle Market Value
- carsxe.get_recall_batchGet Recall Batch
- carsxe.get_vehicle_specsGet Vehicle Specifications
- carsxe.get_vehicle_imagesGet Vehicle Images
- carsxe.get_vehicle_historyGet Vehicle History
- carsxe.get_vehicle_recallsGet Vehicle Recalls
- carsxe.get_year_make_model_dataGet Year Make Model Data
- carsxe.check_lien_and_theftCheck Lien and Theft Records
write
4Create and change things. Allow, or ask the user first.
- carsxe.decode_obd_codeDecode OBD Code
- carsxe.submit_recall_batchSubmit Recall Batch
- carsxe.decode_license_plateDecode License Plate
- carsxe.recognize_license_plateRecognize License Plate
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
CarsXE in three steps.
- 01Your users connect CarsXEThey add their CarsXE api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, and writes like “decode OBD Code” can wait for the user to approve.
- 03Any agent can actYour agent calls CarsXE through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('carsxe', { read: 'allow', write: 'ask', // decode_obd_code destructive: 'deny', }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How CarsXE connects.
Users add their CarsXE 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 CarsXE 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 CarsXE from any agent.
ClaudeChatGPTCursor
Codex
VS CodeOpenAI Agents SDKClaude Agent SDK
Vercel AI SDK
Mastra
LangGraph
CarsXE and Arc0, answered.
Can I use CarsXE with Claude, ChatGPT or Cursor?
Yes. Connect CarsXE 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 CarsXE actions you allow.
How do users connect CarsXE?
Users add their CarsXE 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 CarsXE actions can my agent take?
12 in total: 8 read, 4 write and 0 destructive, such as “decode OBD Code”. Your policies decide which of them each agent may call.
Can I make my agent read-only in CarsXE?
Yes. Allow read actions and deny writes in the CarsXE policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call CarsXE too?
Yes. The same CarsXE connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug CarsXE into your agent.
Your users connect CarsXE once, under your brand. Your agent gets 12 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan