Fidel API for AI agents
Fidel API links payment cards to mobile and web applications for real-time transaction monitoring and card-linked offers, used by fintechs building rewards and loyalty programs. 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 Fidel API.
Check a transaction record
Get a transaction to confirm it matched a card-linked offer before crediting a reward.
List locations under a brand
List the locations tied to a brand to confirm coverage before launching an offer.
Confirm before deleting an offer
Require approval before deleting an offer, since it stops rewards for every linked location.
39 Fidel API actions, graded by risk.
Every Fidel API action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
22Look things up. Allowed by default.
- fidel_api.get_midGet MID
- fidel_api.get_brandGet Brand
- fidel_api.get_offerGet Offer
- fidel_api.list_midsList MIDs
- fidel_api.list_cardsList Cards
- fidel_api.get_programGet Program
- fidel_api.get_webhookGet Webhook
- fidel_api.list_brandsList Brands
- fidel_api.list_offersList Offers
- fidel_api.get_locationGet Location
- fidel_api.list_programsList Programs
- fidel_api.list_locationsList Locations
- fidel_api.get_mid_requestGet MID Request
- fidel_api.get_transactionGet Transaction
- fidel_api.list_mid_requestsList MID Requests
- fidel_api.list_transactionsList Transactions
write
14Create and change things. Allow, or ask the user first.
- fidel_api.create_brandCreate Brand
- fidel_api.create_offerCreate Offer
- fidel_api.update_brandUpdate Brand
- fidel_api.update_offerUpdate Offer
- fidel_api.create_programCreate Program
- fidel_api.update_programUpdate Program
- fidel_api.update_webhookUpdate Webhook
- fidel_api.create_locationCreate Location
- fidel_api.create_mid_requestCreate MID Request
- fidel_api.create_brand_webhookCreate Brand Webhook
- fidel_api.create_program_webhookCreate Program Webhook
- fidel_api.link_location_to_offerLink Location to Offer
- fidel_api.unlink_location_from_offerUnlink Location From Offer
- fidel_api.link_all_program_locations_to_offerLink All Program Locations to Offer
destructive
3Delete, cancel or archive. Ask first, or deny outright.
- fidel_api.delete_offerDelete Offer
- fidel_api.delete_locationDelete Location
- fidel_api.delete_program_webhookDelete Program Webhook
Fidel API in three steps.
- 01Your users connect Fidel APIThey add their Fidel API api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, writes like “create Brand” can wait for the user, and “delete Offer” can be denied outright.
- 03Any agent can actYour agent calls Fidel API through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('fidel_api', { read: 'allow', write: 'ask', // create_brand destructive: 'deny', // delete_offer }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Fidel API connects.
Users add their Fidel API 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 Fidel API 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 Fidel API from any agent.
Fidel API and Arc0, answered.
Can I use Fidel API with Claude, ChatGPT or Cursor?
Yes. Connect Fidel API 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 Fidel API actions you allow.
How do users connect Fidel API?
Users add their Fidel API 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 Fidel API actions can my agent take?
39 in total: 22 read, 14 write and 3 destructive, such as “create Brand”. Your policies decide which of them each agent may call.
Can I stop my agent from deleting things in Fidel API?
Yes. Actions like “delete Offer” 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 Fidel API too?
Yes. The same Fidel API connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Fidel API into your agent.
Your users connect Fidel API once, under your brand. Your agent gets 39 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan