Official vendor OpenAPI document · agent-readyMediaContent Deliverybasic, apiKey (both optional)97 EndpointsREST
For Agents
List and retrieve Pokemon, moves, abilities, items, berries, locations, evolution chains, and related game reference data across 97 read-only endpoints.
Use for: look up a Pokemon by name or id, list all abilities, get the details of a move, find the evolution chain for a species
Not supported: Reads Pokemon game reference data: species, moves, abilities, items, locations, and evolution data. Does not manage game saves, accounts, or any writable state.
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.
Install Jentic One Beta
Connect the PokeAPI to your agent
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the PokeAPI, 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.
1
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%2Fpokeapi.co%2Fpokeapi" | sh2
Step 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%2Fpokeapi.co%2Fpokeapi" | 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.
Capabilities
What an agent can do with PokeAPI API.
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
Patterns agents use PokeAPI API for, with concrete tasks.
★ 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.
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.
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.
List the items in the 'healing' item category and return their effects
Key Endpoints
97 endpoints — the pokeapi serves detailed, read-only data from the pokemon video-game series through a restful interface.
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
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
Jentic AI Readiness Score
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.
P
PokéAPI
- Foundational (C-)52/100
63
Foundational Compliance61
Developer Experience & Jentic Compatibility41
AI-Readiness & Agent Experience85
Agent Usability30
Security72
AI DiscoverabilityPowered by JenticScoring Framework 1.0.0 | Scoring Engine 0.4.2
Show dimension breakdown
63
Foundational Compliance
Base layer of spec validity and structural soundness.
Grade: BSignals: 4
53%
Lint Results
Aggregated quality score from linter diagnostics, weighted by severity.
100%
Resolution Completeness
Percentage of `$ref` references that resolve successfully.
0%
Specification Validity
Checks whether the API description parses successfully and conforms to its declared specification (e.g., OpenAPI).
100%
Structural Integrity
Structural correctness score based on schema issues using logarithmic dampening.
61
Developer Experience & Jentic Compatibility
Clarity, completeness, and ingestion readiness for developers and tooling.
Grade: B-Signals: 4
18%
Example Density
How richly the API is illustrated with examples.
100%
Example Validity
Percentage of examples that conform to their schemas.
25%
Response Coverage
Percentage of operations with complete response definitions (success, client error, server error).
100%
Tooling Readiness
Health of API ingestion, bundling, and resolution within Jentic pipelines.
41
AI-Readiness & Agent Experience
Semantic breadth, depth, and agent comprehension for AI systems.
Grade: D-Signals: 4
13%
Description Coverage
Coverage of descriptions across API elements.
0%
Error Standardization
Coverage of RFC 9457 Problem Details for error responses.
100%
OperationId Quality
Coverage, uniqueness, and casing consistency of operationIds for AI inference.
49%
Summary Coverage
Coverage of summaries across operations/tags/info.
85
Agent Usability
Functional utility, complexity comfort, and AI orchestration readiness.
Grade: ASignals: 1
85%
Complexity Comfort
Agent comfort level based on API operational and structural complexity.
30
Security
Trust, risk posture, and security compliance.
Grade: FSignals: 1
30%
Authentication Strength
Average quality of security schemes based on authentication method strength (weakest link for OAuth2).
72
AI Discoverability
Findability, semantic richness, and reasoning readiness.
Grade: A-Signals: 1
72%
Descriptive Richness
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>Why Jentic?
What agents get from Jentic-routed access to this vendor.
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 isolation
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.
Intent-based discovery
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
Alternatives and complements available in the Jentic catalogue.
FAQs
Specific to using PokeAPI API through Jentic.
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.
GET STARTED