Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Pokemon TCG 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%2Fpokemontcg.io%2Fpokemontcg" | 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%2Fpokemontcg.io%2Fpokemontcg" | 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 Pokemon TCG API.
Search Pokemon trading cards by name, type, set, and rarity
Retrieve a single card by its id with full details
Search card sets and retrieve set details
List the card types, subtypes, and supertypes in the game
List the rarities used across the card game
GET STARTED
Patterns agents use Pokemon TCG API for, with concrete tasks.
★ AI Card Data Agent
An AI agent connected to the Pokemon TCG API through Jentic can answer questions about cards by searching the catalog, retrieving a card by id, and reading its set and rarity. Because the data is free to query, the agent can resolve card references for deck tools or chat assistants without a paid data source.
Search cards for a name, retrieve the top match by id, and report its set and rarity
Card Search and Lookup
Search Pokemon cards with query filters for name, type, set, and rarity, then fetch the full record of a chosen card by id. The API returns structured card data an application can display or index.
Search for cards of a given type in a specific set and retrieve the first result by id
Set and Reference Data
Build card tools on top of the game's reference data: sets, types, subtypes, supertypes, and rarities. The API lists each of these so an application can populate filters and validate user input against real values.
List the available sets and the full set of card rarities to populate a filter
8 endpoints — the pokemon tcg api provides access to pokemon trading card game data, letting you search cards by name, type, set, and rarity and retrieve full card details by id.
METHOD
PATH
DESCRIPTION
/cards
Search cards
/cards/{id}
Get a card by id
/sets
Search sets
/sets/{id}
Get a set by id
/types
List card types
/rarities
List card rarities
/cards
Search cards
/cards/{id}
Get a card by id
/sets
Search sets
/sets/{id}
Get a set by id
/types
List card types
/rarities
List card rarities
What agents get from Jentic-routed access to this vendor.
Setup
Wiring the Pokemon TCG API by hand means attaching an optional key header and learning its card, set, and reference endpoints yourself. Through Jentic you install once, import it from the API Directory, store the key once, and your agent calls it.
Permission scoping
The Pokemon TCG API is read-only and carries its filters in the query string, so a rule bounds which operations your agent may call rather than which query. A rule can allow card and set lookups while leaving the type and rarity listings out unless you add them.
Credential isolation
Your Pokemon TCG 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 'search for a Pokemon card', and Jentic returns the matching Pokemon TCG operation with its input schema so the agent calls the right endpoint without browsing the reference docs.
Alternatives and complements available in the Jentic catalogue.
Specific to using Pokemon TCG API through Jentic.
Is there a Pokemon TCG MCP server?
You don't need an MCP server to give your agent the Pokemon TCG API. Jentic connects it directly from the API Directory: import it, store your optional API key once, and your agent can search cards and sets. Operations are discovered on demand, so your agent's context stays lean.
Can I limit what my agent is allowed to do with the Pokemon TCG API?
Yes. The Pokemon TCG API is read-only and carries its filters in the query string, so a rule bounds which operations your agent may call. Write a rule that allows only card and set lookups, leaving the type and rarity listings out unless you add them, and every call is logged.
What authentication does the Pokemon TCG API use?
The Pokemon TCG API accepts an optional API key sent in the X-Api-Key header per its OpenAPI spec, and providing one raises your rate limits. With Jentic, the key is stored encrypted by your own Jentic One instance and injected at call time.
Can I search for a card by rarity with the Pokemon TCG API?
Yes. The cards endpoint accepts query filters for name, type, set, and rarity, so an agent can narrow results to a specific rarity. You can then retrieve the full record of a matching card by its id.
What are the rate limits for the Pokemon TCG API?
The spec notes that an API key raises your rate limits but does not state the numbers. Check the Pokemon TCG developer documentation at https://docs.pokemontcg.io for current limits.
How do I search for a card with the Pokemon TCG API through Jentic?
Import the Pokemon TCG API from the Jentic API Directory, store your optional API key once, and have your agent search by intent such as 'search for a Pokemon card'. Jentic returns the search operation with its input schema, and your agent passes the query filters. To run it on your own infrastructure, install Jentic One from its GitHub repo.
For Agents
Search Pokemon Trading Card Game cards by name, type, set, and rarity, retrieve card and set details, and list types, subtypes, supertypes, and rarities. Free to use with an optional API key.
Use for: Search for a Pokemon card by name, Get the details of a specific card, Find all cards in a particular set, List the available card sets
Not supported: Does not handle deck building, user accounts, or marketplace transactions. Use for Pokemon TCG card and set data lookup only.
The Pokemon TCG API provides access to Pokemon Trading Card Game data, letting you search cards by name, type, set, and rarity and retrieve full card details by id. It also serves card sets and the reference lists of types, subtypes, supertypes, and rarities used across the game. The API is free to use, with an optional API key that raises rate limits.
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>