Remote Retrieval for AI agents

Remote Retrieval coordinates equipment retrieval logistics, letting IT teams create and track return orders for laptops and monitors from remote employees. 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.

DevOps and monitoringAPI keyMCP + REST
AUDIT LOG · REMOTE RETRIEVALPOLICY: acme-support
09:41:07 · claude · u_8f2read
remote_retrieval.list_pending_orders
List Pending Orders✓ allowed · 212ms
09:41:08 · claude · u_8f2read
remote_retrieval.validate_user
RemoteRetrieval: Validate User✓ allowed · 164ms
09:41:09 · claude · u_8f2write
remote_retrieval.create_order
Create Order✓ approved · approved by user
EVERY REMOTE RETRIEVAL CALL, ON THE RECORD
01 · USE CASES

What agents do in Remote Retrieval.

01

Check pending returns

List pending orders to see which employees still have equipment to send back.

02

Look up device pricing

Get device prices before deciding how to handle a lost or damaged laptop.

03

Confirm before creating an order

Get the order details and company account first, then create a new retrieval order only after review.

02 · ACTIONS

7 Remote Retrieval actions, graded by risk.

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

read

6

Look things up. Allowed by default.

  • remote_retrieval.get_all_orders
    Get All Orders
  • remote_retrieval.get_device_prices
    Get Device Prices
  • remote_retrieval.get_order_details
    Get Order Details
  • remote_retrieval.get_company_details
    Get Company Details
  • remote_retrieval.list_pending_orders
    List Pending Orders
  • remote_retrieval.validate_user
    RemoteRetrieval: Validate User

write

1

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

  • remote_retrieval.create_order
    Create Order

destructive

0

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

  • No destructive actions.
03 · HOW IT WORKS

Remote Retrieval in three steps.

  1. 01Your users connect Remote RetrievalThey add their Remote Retrieval api key on Arc0 Connect, under your brand. It goes straight into the vault.
  2. 02You set the rulesReads run, and writes like “create Order” can wait for the user to approve.
  3. 03Any agent can actYour agent calls Remote Retrieval 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('remote_retrieval', {
  read: 'allow',
  write: 'ask',        // create_order
  destructive: 'deny',  
})

# 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 Remote Retrieval connects.

Users add their Remote Retrieval 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 Remote Retrieval 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 Remote Retrieval from any agent.

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

Remote Retrieval and Arc0, answered.

Q01

Can I use Remote Retrieval with Claude, ChatGPT or Cursor?

Yes. Connect Remote Retrieval 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 Remote Retrieval actions you allow.

Q02

How do users connect Remote Retrieval?

Users add their Remote Retrieval 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 Remote Retrieval actions can my agent take?

7 in total: 6 read, 1 write and 0 destructive, such as “create Order”. Your policies decide which of them each agent may call.

Q04

Can I make my agent read-only in Remote Retrieval?

Yes. Allow read actions and deny writes in the Remote Retrieval policy. Your agent can still look things up, and any write it attempts is blocked and logged.

Q05

Can my own backend call Remote Retrieval too?

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

Get started

Plug Remote Retrieval into your agent.

Your users connect Remote Retrieval once, under your brand. Your agent gets 7 actions behind your policies, with every call on the record.

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