Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Cards API, or any other public or private API you need. You set the rules, the agent never sees your credentials, and every call is logged.
Two steps, two machines. Install the instance in a safe environment, then register your agent from wherever it runs.
Step 1: Jentic One Host machine
# On the machine that will host your Jentic One instance:
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Fmcards.com%2Fmcards" | shStep 2: Agent machine
# On the machine where your agent runs (keep this separate from the instance):
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Fmcards.com%2Fmcards" | sh
jentic register # connects your agent to your Jentic One instanceJentic One is in public beta. The setup above keeps your agent separate from the instance, which is what you want before using real credentials: an agent running as the same OS user as Jentic One can read its stored keys directly. Just evaluating? A single local install is fine to start. See the secure deployment guide for the tiers.
What an agent can do with Cards API.
Retrieve a distributor's cards and the details of a specific distributor card
List the cardholder cards issued under a distributor card
Look up a cardholder card and the payment accounts linked to it
Read transaction history for a cardholder card or a specific payment account
Trace linked bank account transactions behind a payment account transaction
GET STARTED
Patterns agents use Cards API for, with concrete tasks.
★ AI Agent Card Data Access
Give an AI agent read access to a card program so it can answer questions about cards, cardholders, and spending. The agent discovers the lookup operations through Jentic, stores the mCards key once, and reads card and transaction records without bespoke HTTP wiring. Because every operation is read-only, the agent reports rather than moves money.
Look up a cardholder card, list its payment accounts, and summarize the recent transactions on each
Transaction Reconciliation
Pull transaction histories for cardholder cards and their payment accounts to reconcile against internal ledgers. The API exposes card transactions and the linked bank account transactions behind them, so a reconciliation job can match each movement end to end.
Retrieve a cardholder card's transactions and the linked bank account transactions for the last statement period
Cardholder Account Lookup
Resolve a cardholder card into its payment accounts and current details for support and servicing. Given a cardholder card identifier, the API returns the card record and each associated payment account so a support agent can confirm account status quickly.
Given a cardholder card identifier, return the card details and every payment account attached to it
Program Reporting
Report on a distributor's card program by walking from distributor cards down to the cardholder cards issued under them. The hierarchy lets a reporting job roll up cardholder counts and transaction activity per distributor.
List a distributor's cards and, for each, count the cardholder cards issued underneath
10 endpoints — the cards api from mcards provides read access to a prepaid card program: distributor cards, the cardholder cards issued beneath them, and the transactions and payment accounts tied to each cardholder.
METHOD
PATH
DESCRIPTION
/api/cards/v1/distributor_cards
List a distributor's cards
/api/cards/v1/distributor_cards/{distributor_card_uuid}
Retrieve a distributor card
/api/cards/v1/cardholder_cards/{cardholder_card_uuid}
Retrieve a cardholder card
/api/cards/v1/cardholder_cards/{cardholder_card_uuid}/transactions
List transactions for a cardholder card
/api/cards/v1/cardholder_cards/{cardholder_card_uuid}/payment_accounts
List payment accounts for a cardholder card
/api/cards/v1/distributor_cards
List a distributor's cards
/api/cards/v1/distributor_cards/{distributor_card_uuid}
Retrieve a distributor card
/api/cards/v1/cardholder_cards/{cardholder_card_uuid}
Retrieve a cardholder card
/api/cards/v1/cardholder_cards/{cardholder_card_uuid}/transactions
List transactions for a cardholder card
/api/cards/v1/cardholder_cards/{cardholder_card_uuid}/payment_accounts
List payment accounts for a cardholder card
What agents get from Jentic-routed access to this vendor.
Setup
Wiring the mCards Cards API by hand means learning its Authorization-header auth and walking the distributor-to-cardholder-to-transaction hierarchy yourself. Through Jentic you install once, import the API from the API Directory, store the key, and your agent calls the read it needs.
Permission scoping
You decide which mCards operations your agent may call. Because every operation is read-only, a rule can expose cardholder lookups and transaction reads while the agent can never create, update, or delete a record.
Credential isolation
Your mCards API key is stored once, encrypted, by your own Jentic One instance and injected at execution time. It never enters the agent's prompt, logs, or context.
Intent-based discovery
Agents search Jentic by intent such as 'list a cardholder card's transactions', and Jentic returns the matching mCards operation with its input schema so the agent calls the right endpoint without reading the reference docs.
Alternatives and complements available in the Jentic catalogue.
Specific to using Cards API through Jentic.
What authentication does the mCards Cards API use?
The Cards API expects an API key in the Authorization header, as declared by its OpenAPI spec. Through Jentic the key is stored encrypted by your own Jentic One instance and injected when a call runs, so it never enters the agent's prompt or logs.
Can the mCards Cards API move money or change cards?
No. Every operation in the spec is a read: it returns card, cardholder, payment account, and transaction records. There are no create, update, or delete operations, so an agent can report on the program but cannot alter it.
What are the rate limits for the mCards Cards API?
The OpenAPI spec does not publish specific rate limits. Check the mCards documentation for current limits, and have your agent back off and retry when it receives a throttling response.
How do I read card data with the mCards Cards API through Jentic?
Search Jentic for an intent like 'look up a cardholder card', and it returns the matching mCards operation with its input schema. Import the connector once, store your key, and your agent reads card and transaction records without hand-written HTTP code. To run it on your own infrastructure, install Jentic One from its GitHub repo.
Is there an mCards MCP server?
You don't need an MCP server to give your agent the mCards Cards API. Jentic connects it directly from the Jentic API Directory: import the API, store your key once, and your agent calls the lookup operations. Operations are discovered on demand, so no extra tool definitions are loaded into the agent's context.
Can I limit what my agent is allowed to do with the mCards Cards API?
Yes. You choose the operations the agent may call, so a rule can allow only the cardholder lookup and transaction reads your workflow needs. Since the API is read-only, the agent can never move funds, and every call is logged.
Know of an official OpenAPI document? Contribute it →
For Agents
Read distributor cards, cardholder cards, payment accounts, and transaction histories from the mCards Cards API.
Use for: I want to list a distributor's cards, Look up a cardholder card by its identifier, Show the transactions for a cardholder card, Find the payment accounts on a cardholder card
Not supported: Does not issue cards, move funds, or change cardholder records. Use it to read distributor cards, cardholder cards, payment accounts, and transactions only.
The Cards API from mCards provides read access to a prepaid card program: distributor cards, the cardholder cards issued beneath them, and the transactions and payment accounts tied to each cardholder. It returns card details, cardholder card lists, and payment account records, along with card and linked bank account transaction histories for reconciliation and reporting.
This API is usable in Jentic One now. Its AI-readiness score against Jentic's framework shows where it stands today and where improvements would make it even easier for agents to use.
Base layer of spec validity and structural soundness.
Aggregated quality score from linter diagnostics, weighted by severity.
Percentage of `$ref` references that resolve successfully.
Checks whether the API description parses successfully and conforms to its declared specification (e.g., OpenAPI).
Structural correctness score based on schema issues using logarithmic dampening.
Clarity, completeness, and ingestion readiness for developers and tooling.
How richly the API is illustrated with examples.
Percentage of examples that conform to their schemas.
Percentage of operations with complete response definitions (success, client error, server error).
Health of API ingestion, bundling, and resolution within Jentic pipelines.
Semantic breadth, depth, and agent comprehension for AI systems.
Coverage of descriptions across API elements.
Coverage of RFC 9457 Problem Details for error responses.
Coverage, uniqueness, and casing consistency of operationIds for AI inference.
Coverage of summaries across operations/tags/info.
Functional utility, complexity comfort, and AI orchestration readiness.
Agent comfort level based on API operational and structural complexity.
Trust, risk posture, and security compliance.
Average quality of security schemes based on authentication method strength (weakest link for OAuth2).
Findability, semantic richness, and reasoning readiness.
Clarity and depth of descriptions across API elements.
Score it yourself
Every API in the directory is allowlisted, so you can re-score it with no key required.
npx @jentic/api-scorecard-cli score <openapi-url>