Boxhero for AI agents

BoxHero is cloud-based inventory management software that small and mid-sized businesses use to track stock levels, locations, and transactions across a team. 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.

Project managementAPI keyMCP + RESTboxhero-app.com
AUDIT LOG · BOXHEROPOLICY: acme-support
09:41:07 · claude · u_8f2read
boxhero.list_items
List Items✓ allowed · 212ms
09:41:08 · claude · u_8f2read
boxhero.get_item
Get Item✓ allowed · 164ms
09:41:12 · claude · u_8f2destructive
boxhero.delete_item
Delete Item✕ blocked · policy: deny
EVERY BOXHERO CALL, ON THE RECORD
01 · USE CASES

What agents do in Boxhero.

01

Check stock levels for an item

Read-only lookup of an item's stock level and location before deciding to reorder or transfer it.

02

Review transaction history

Pull the basic or location transaction history for an item to see its recent stock movements.

03

Require approval before deleting an item

Flag deleting an item or location as destructive since it removes inventory records.

02 · ACTIONS

14 Boxhero actions, graded by risk.

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

read

12

Look things up. Allowed by default.

  • boxhero.get_item
    Get Item
  • boxhero.get_member
    Get Member
  • boxhero.list_items
    List Items
  • boxhero.get_location
    Get Location
  • boxhero.list_members
    List Team Members
  • boxhero.get_team_info
    Get Linked Team Info
  • boxhero.list_partners
    BoxHero - List Partners
  • boxhero.list_locations
    BoxHero - List Locations
  • boxhero.get_item_attribute
    Get Item Attribute
  • boxhero.list_item_attributes
    List Item Attributes
  • boxhero.list_basic_transactions
    BoxHero - List Basic Transactions
  • boxhero.list_location_transactions
    BoxHero - List Location Transactions

write

0

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

  • No write actions.

destructive

2

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

  • boxhero.delete_item
    Delete Item
  • boxhero.delete_location
    BoxHero - Delete Location
03 · HOW IT WORKS

Boxhero in three steps.

  1. 01Your users connect BoxheroThey add their Boxhero api key on Arc0 Connect, under your brand. It goes straight into the vault.
  2. 02You set the rulesReads run, writes like “updates” can wait for the user, and “delete Item” can be denied outright.
  3. 03Any agent can actYour agent calls Boxhero 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('boxhero', {
  read: 'allow',
  write: 'ask',        
  destructive: 'deny',  // delete_item
})

# 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 Boxhero connects.

Users add their Boxhero 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 Boxhero 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 Boxhero from any agent.

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

Boxhero and Arc0, answered.

Q01

Can I use Boxhero with Claude, ChatGPT or Cursor?

Yes. Connect Boxhero 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 Boxhero actions you allow.

Q02

How do users connect Boxhero?

Users add their Boxhero 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 Boxhero actions can my agent take?

14 in total: 12 read, 0 write and 2 destructive. Your policies decide which of them each agent may call.

Q04

Can I stop my agent from deleting things in Boxhero?

Yes. Actions like “delete Item” 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 Boxhero too?

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

Get started

Plug Boxhero into your agent.

Your users connect Boxhero once, under your brand. Your agent gets 14 actions behind your policies, with every call on the record.

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