canonical: https://jentic.com/apis/tcgdex.net/tcgdex

# TCGdex API

A Multilanguage Pokémon TCG Database with Cards Pictures and most of the informations contained on the cards. You can find out more about TCGdex at [https://www.tcgdex.net](https://www.tcgdex.net) or on [Discord](https://discord.gg/NehYTAhsZE). The API exposes 33 endpoints.

## For AI agents

Programmatically fetch the list of cards, finds card by global id. Covers 33 operations.

## Scope

Does not handle payments, communications, or crm - use for developer tools only.

## Capabilities

- fetch the list of cards
- Finds Card by Global ID
- Integrate TCGdex API into automated workflows
- Query and filter TCGdex API records by parameters
- Monitor TCGdex API operational status and events

## Use cases

### Developer Tools Operations

Use the TCGdex API to perform developer tools operations programmatically. The API provides 33 endpoints covering core functionality including fetch the list of cards, finds card by global id.

Example prompt: Call GET /cards to fetch the list of cards

### Data Retrieval and Monitoring

Query TCGdex API resources on a schedule to track changes, generate alerts, or feed downstream dashboards. Agents poll relevant endpoints, compare against previous state, and trigger actions when thresholds are crossed.

Example prompt: Poll the primary TCGdex API endpoint, compare response to last known state, and alert if changed

### AI Agent Integration via Jentic

AI agents discover and call TCGdex API endpoints through Jentic without managing credentials directly. An agent searches for the required operation by intent, receives the matching endpoint schema, and executes the call with Jentic-managed authentication. This eliminates the need to read API documentation or handle none tokens manually.

Example prompt: Search Jentic for 'fetch the list of cards', load the operation schema, and execute with Jentic-managed credentials

## Key endpoints

| Method | Path | Description |
| --- | --- | --- |
| GET | `/cards` | fetch the list of cards |
| GET | `/cards/{cardId}` | Finds Card by Global ID |

## Key resources

- **cards** — Fetch cards globally
- **filters** — differents requests to filter cards

## AI readiness

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.

- **Score:** 10 / 100
- **Maturity:** Non-Ready
- **Dimensions:**
  - Foundational Compliance: 99 / 100
  - Developer Experience & Jentic Compatibility: 65 / 100
  - AI-Readiness & Agent Experience: 7 / 100
  - Agent Usability: 94 / 100
  - Security: 100 / 100
  - AI Discoverability: 2 / 100
- **View full report:** https://jentic.com/apis/tcgdex.net/tcgdex/scorecard
- **How the score is calculated:** https://docs.jentic.com/reference/api-readiness-framework/overview/
- **More about the dimensions:** https://docs.jentic.com/reference/api-readiness-framework/specification/#dimensional-model-overview

### Score it yourself

Every API in the directory is allowlisted, so you can re-score it with no key required.

- **Score your own API:** https://jentic.com/scorecard.md
- **Scoring CLI agent skill:** https://github.com/jentic/jentic-api-scorecard/blob/main/skills/jentic-api-scorecard/SKILL.md

```sh
npx @jentic/api-scorecard-cli score <openapi-url>
```

## Why Jentic

- **Setup:** The TCGdex API needs no auth credential, but wiring it by hand still means filling the language segment in its api.tcgdex.net/v2/{lang} host, tracking its card paths, and building your own retry handling. Through Jentic you install once, import the TCGdex API from the API Directory, and your agent calls it.
- **Permission scoping:** The TCGdex API puts the card id in the URL path (`/cards/{cardId}`), so a rule can pin your agent to reading a specific card, and its listed operations only read card data. You choose the operations it may call, and none of them change state, so nothing destructive is included.
- **Credential handling:** The TCGdex API needs no credential, so there is nothing for the agent to hold; any configuration your Jentic One instance stores is kept encrypted and never enters the agent's prompt, logs, or context.
- **Discovery method:** Agents search Jentic by intent such as 'fetch the list of cards' or 'get a card by id', and Jentic returns the matching TCGdex API operation with its input schema so the agent calls the right endpoint without browsing the reference docs.

## Related APIs

- **Github** — Alternative developer tools API
- **Gitlab** — Alternative developer tools API

## FAQ

### What authentication does the TCGdex API use?

The TCGdex API uses no authentication. Through Jentic, these credentials are stored encrypted in your Jentic One instance and injected at execution time, so raw secrets never enter the agent context.

### Can I fetch the list of cards with the TCGdex API?

Yes. Use the GET /cards endpoint. The API returns structured JSON responses that agents can parse and act on directly.

### What are the rate limits for the TCGdex API?

Rate limits are not specified in the OpenAPI spec. Check the vendor documentation for current limits. Through Jentic, rate limiting is handled automatically with retry logic built into the execution layer.

### How do I fetch the list of cards through Jentic?

Install the Jentic SDK with pip install jentic, authenticate through Jentic One, the self-hosted execution layer, then search for 'fetch the list of cards'. Jentic returns the matching TCGdex API operation with its input schema. Load the schema and execute the call - credentials are injected automatically.

### How many endpoints does the TCGdex API have?

The TCGdex API exposes 33 endpoints covering cards, filters operations.

### Can I limit what my agent is allowed to do with the TCGdex API?

Yes. Jentic One is self-hosted, so you set the rules that decide which TCGdex API operations your agent may call, and every operation it exposes only reads card data, so none of them change state. Because the card id sits in the URL path at GET `/cards/{cardId}`, you can pin the agent to reading a specific card rather than fetching the full list at GET /cards. You choose the operations it can reach, and nothing destructive is included.