canonical: https://jentic.com/apis/pokeapi.co/pokeapi

# PokeAPI

The PokeAPI serves detailed, read-only data from the Pokemon video-game series through a RESTful interface. It lists and retrieves resources across abilities, berries, moves, items, locations, evolution chains, generations, and the Pokemon themselves, with each resource offering a paged list and a by-id lookup. The public data needs no credential, so an agent can query the full reference dataset to answer questions, build game tools, or enrich content.

## For AI agents

List and retrieve Pokemon, moves, abilities, items, berries, locations, evolution chains, and related game reference data across 97 read-only endpoints.

## Scope

Reads Pokemon game reference data: species, moves, abilities, items, locations, and evolution data. Does not manage game saves, accounts, or any writable state.

## Capabilities

- List and retrieve Pokemon and their forms and species data
- Look up moves, abilities, and their categories and effects
- Query items, item categories, attributes, and pockets
- Read locations, location areas, and encounter data
- Traverse evolution chains, triggers, and generations
- Read berries, contest types, and other reference resources

## Use cases

### Game reference assistant

An AI agent answers questions about the Pokemon games by retrieving a Pokemon, move, or ability and returning its stats and effects, backing a chatbot or study tool with authoritative data.

Example prompt: Look up the Pokemon 'pikachu' and return its types, base stats, and abilities

### Team-building tool

An agent reads moves, abilities, and evolution chains to help a user assemble or evaluate a team, pulling the exact reference numbers behind each choice.

Example prompt: Return the evolution chain for the species 'eevee' and list each stage

### Content enrichment

An agent enriches a fan site or dataset by pulling item, berry, and location data, keeping generated content grounded in the canonical game data.

Example prompt: List the items in the 'healing' item category and return their effects

## Key endpoints

| Method | Path | Description |
| --- | --- | --- |
| GET | `/api/v2/ability/` | List abilities |
| GET | `/api/v2/ability/{id}/` | Retrieve an ability by id |
| GET | `/api/v2/move/` | List moves |
| GET | `/api/v2/item/{id}/` | Retrieve an item by id |
| GET | `/api/v2/evolution-chain/{id}/` | Retrieve an evolution chain |
| GET | `/api/v2/generation/` | List generations |

## Key resources

- **Pokemon** — Species, forms, stats, types, and abilities
- **Moves** — Moves, categories, damage classes, and effects
- **Abilities** — Abilities and their effects on Pokemon
- **Items** — Items, categories, attributes, and pockets
- **Locations and evolution** — Locations, encounters, evolution chains, and generations

## 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:** 52 / 100
- **Maturity:** Foundational
- **Dimensions:**
  - Foundational Compliance: 63 / 100
  - Developer Experience & Jentic Compatibility: 61 / 100
  - AI-Readiness & Agent Experience: 41 / 100
  - Agent Usability: 85 / 100
  - Security: 30 / 100
  - AI Discoverability: 72 / 100
- **View full report:** https://jentic.com/apis/pokeapi.co/pokeapi/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:** Wiring the PokeAPI by hand means paging through resource lists and following resource URLs across 97 read endpoints yourself. Through Jentic you install once, import the PokeAPI from the Directory, and your agent calls it with no credential to configure.
- **Permission scoping:** Every operation is a read, so scope by operation: allow the agent only the resource lists and lookups it needs, such as Pokemon, moves, or items, and withhold the rest. None of the operations change data.
- **Credential handling:** The PokeAPI serves public data and needs no credential. If you configure the optional HTTP Basic or session-cookie authentication, your own Jentic One instance stores it encrypted and injects it at execution time, so it never enters the agent's prompt, logs, or context.
- **Discovery method:** Agents search Jentic by intent, such as 'look up a Pokemon by name' or 'find the evolution chain for a species', and Jentic returns the matching PokeAPI operation with its input schema so the agent calls the right endpoint without reading the reference docs by hand.

## Related APIs

- **D&D 5e API** — Open read-only reference data for Dungeons & Dragons 5e
- **RAWG Video Games API** — Broad video-game database across titles and platforms
- **SuperHero API** — Read-only character stats and biography data

## FAQ

### What can an AI agent do with the PokeAPI?

An agent can list and retrieve Pokemon, moves, abilities, items, berries, locations, evolution chains, and generations, giving it the full read-only reference dataset for the games.

### How do I connect the PokeAPI to an AI agent with Jentic?

Import the PokeAPI from the Jentic API Directory and your agent can call it right away, since the public data needs no credential. To get started, install the self-hosted Jentic One runtime from its GitHub repository and import the PokeAPI from the Jentic API Directory.

### Does the PokeAPI need an API key?

No credential is required for the public data. The spec declares optional HTTP Basic and session-cookie schemes, but everyday reads work without either, and Jentic One can hold either credential encrypted if you configure one.

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

Yes. Every operation is a read, so scope the agent by operation: permit only the resource lists and lookups it needs, such as Pokemon and moves, and withhold the rest.

### Can I write or change data through the PokeAPI?

No. It is a read-only reference API, so it returns game data but does not accept changes, and it should be treated as a shared public resource with fair-use caching.