Fidel API MCP integration for AI agents.
Connect AI agents to Fidel API through 6 structured actions, including get brand, get card, and get transaction. Review authentication, inputs, workflows, an…
- ACTION CONTRACTS
- 6
- AUTHENTICATION
- API key
- SOURCE STATUS
- Provider-backed
CATALOG SOURCE REVIEWED AUGUST 23, 2026 / ACTION NAMES AND SCHEMAS DERIVED FROM WORKING MACHINES PROVIDER SOURCE
CAPABILITY PROFILE
What the Fidel API integration exposes
The Fidel API Agent App exposes 6 provider-backed actions for finance and data work. Its current contract lets an authorized agent fetch one fidel brand by brand id, fetch one fidel card by card id, and fetch one fidel transaction by transaction id. These operations are called through Working Machines as typed capabilities rather than through browser navigation or copied UI steps.
A connection uses API key. Before execution, the agent can inspect the selected action, its required fields, declared scopes, and expected output contract. Provider credentials remain inside the Working Machines runtime; the calling agent receives the capability and its structured result, not the underlying secret.
For reliable operation, start with the narrowest action that satisfies the task, resolve stable provider identifiers before changing state, and validate the returned object or status after execution. Availability still depends on the connected Fidel API account, granted provider permissions, workspace policy, region, plan, and upstream API behavior.
VERIFIED ACTION SAMPLE
Real Fidel API capabilities.
Showing 6 of 6 actions. Risk labels are conservative signals based on operation names, not substitutes for provider documentation or runtime policy.
get_brandREADFetch one Fidel brand by brand ID.
INPUTS: brandId
get_cardREADFetch one Fidel card by card ID.
INPUTS: cardId
get_transactionREADFetch one Fidel transaction by transaction ID.
INPUTS: transactionId
list_brandsREADList Fidel brands available to the connected secret API key.
INPUTS: limit / start / order / name
list_cardsREADList Fidel cards for one program ID.
INPUTS: programId / limit / start / order
list_transactionsREADList Fidel transactions for one program ID.
INPUTS: programId / limit / start / order / from
INPUT CONTRACTS
Know what the action needs before it runs.
get_brand
brandIdREQUIRED- The Fidel brand ID to fetch.
get_card
cardIdREQUIRED- The Fidel card ID to fetch.
get_transaction
transactionIdREQUIRED- The Fidel transaction ID to fetch.
list_brands
limitOPTIONAL- The maximum number of brands to return.
startOPTIONAL- The opaque cursor string returned as nextCursor by a previous Fidel list action. Pass it back unchanged.
orderOPTIONAL- Sort order for the upstream created or datetime field.
nameOPTIONAL- Filter brands by name.
PROVIDER-SPECIFIC WORKFLOWS
Jobs this Agent App can support
Inspect Get Brand
Fetch one Fidel brand by brand ID. Use this as a bounded discovery step, retain the returned identifier, and avoid expanding the read beyond the task's stated scope.
get_brandVerify with Get Card
Fetch one Fidel card by card ID. Compare the returned provider state with the intended outcome and preserve stable IDs or canonical links in the run record.
get_cardSAFETY BOUNDARY
Operate Fidel API with explicit limits
- Authorize Fidel API with API key and grant only the provider access required by the selected actions.
- The current action names appear read-oriented, but returned Fidel API data may still be sensitive and should be minimized before it enters model context.
- Do not infer permission from catalog visibility. Workspace policy, connection identity, and upstream authorization still govern execution.
- No provider scope string is declared on the sampled actions. Verify the connected account's actual permissions in Fidel API rather than assuming unrestricted access.
- After a call, inspect the structured result and execution record before reporting that the Fidel API task completed successfully.
CONNECTION MODEL
API key
Fidel API secret key used with the Fidel-Key header for read-only brands, cards, and transactions endpoints. Create or sign in to the Fidel dashboard to get your test or live secret key: https://dashboard.fidel.uk/sign-in
Working Machines stores provider credentials behind the execution boundary. An agent can use an authorized connection identity, but catalog discovery alone does not reveal OAuth tokens, API keys, or provider secrets.
- READ SIGNALS
- 6
- WRITE SIGNALS
- 0
- HIGH IMPACT
- 0
- REVIEW SIGNALS
- 0
EVIDENCE AND AVAILABILITY
Provider reference
Action names, input fields, authentication types, and counts on this page are generated from the Working Machines provider catalog. Provider behavior, quotas, object semantics, account eligibility, and regional availability remain governed by Fidel API.