Codereadr for AI agents
CodeREADr turns phones into barcode scanners for field data collection, letting a business validate scans and pull reporting from the field. 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 Codereadr.
Retrieve scan records
Retrieve scan records from a service to see what was captured in the field.
Check registered devices
Check which devices are registered to a service before adding a new scanner.
Confirm before deleting a service
Confirm before deleting a scanning service, since its scan history and questions go with it.
16 Codereadr actions, graded by risk.
Every Codereadr action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
5Look things up. Allowed by default.
- codereadr.list_supported_barcode_typesList Supported Barcode Types
- codereadr.retrieve_scansRetrieve Scan Records
- codereadr.retrieve_devicesRetrieve Devices
- codereadr.retrieve_servicesRetrieve CodeREADr Services
- codereadr.retrieve_databasesRetrieve CodeREADr Databases
write
6Create and change things. Allow, or ask the user first.
- codereadr.create_serviceCreate CodeREADr Service
- codereadr.update_serviceUpdate CodeREADr Service
- codereadr.update_questionUpdate CodeREADr Question
- codereadr.generate_scan_linkGenerate Scan Link
- codereadr.configure_connectorConfigure CodeREADr Connector
- codereadr.collect_data_with_questionsCollect Data With Questions
destructive
5Delete, cancel or archive. Ask first, or deny outright.
- codereadr.delete_userDelete CodeREADr User
- codereadr.delete_deviceDelete Device
- codereadr.delete_serviceDelete CodeREADr Service
- codereadr.delete_databaseDelete CodeREADr Database
- codereadr.delete_questionDelete Custom Question
Codereadr in three steps.
- 01Your users connect CodereadrThey add their Codereadr api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, writes like “create CodeREADr Service” can wait for the user, and “delete CodeREADr User” can be denied outright.
- 03Any agent can actYour agent calls Codereadr through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('codereadr', { read: 'allow', write: 'ask', // create_service destructive: 'deny', // delete_user }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Codereadr connects.
Users add their Codereadr 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 Codereadr 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 Codereadr from any agent.
Codereadr and Arc0, answered.
Can I use Codereadr with Claude, ChatGPT or Cursor?
Yes. Connect Codereadr 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 Codereadr actions you allow.
How do users connect Codereadr?
Users add their Codereadr 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 Codereadr actions can my agent take?
16 in total: 5 read, 6 write and 5 destructive, such as “create CodeREADr Service”. Your policies decide which of them each agent may call.
Can I stop my agent from deleting things in Codereadr?
Yes. Actions like “delete CodeREADr User” 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.
Can my own backend call Codereadr too?
Yes. The same Codereadr connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Codereadr into your agent.
Your users connect Codereadr once, under your brand. Your agent gets 16 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan