Compatible with every major AI agent and IDE
What is the Poké MCP Server?
Connect to the PokéAPI through this MCP server to explore the vast world of Pokémon data. This integration allows any AI agent to retrieve detailed information about items, mechanics, and world interactions.
What you can do
- Berry Research — List all berries, check their firmness levels, and explore flavor profiles like spicy, dry, or sweet.
- Contest Mastery — Query contest types and effects to understand how different moves and items perform in competition.
- Encounter Methods — Discover the various ways Pokémon can be encountered in the wild, from walking in tall grass to fishing.
- Data Exploration — Access paginated lists of resources to browse the entire database systematically.
How it works
- Subscribe to this server
- Initialize the connection (no complex keys required for public data)
- Start querying Pokémon lore and mechanics from Claude, Cursor, or any MCP client
Who is this for?
- Game Developers — quickly reference Pokémon mechanics and item data while coding or designing.
- Content Creators — verify facts about berries and contests for guides or wikis without leaving the chat interface.
- Data Enthusiasts — explore the structured relationships of the Pokémon world through natural language.
Built-in capabilities (49)
Get berry details
Get berry firmness details
Get berry flavor details
Get contest effect details
Get contest type details
Get encounter condition details
Get encounter condition value details
Get encounter method details
Get evolution chain details
Get evolution trigger details
Get generation details
Get item details
Get item attribute details
Get item category details
Get item fling effect details
Get item pocket details
Get location details
Get location area details
Get pal park area details
Get pokedex details
Get region details
Get super contest effect details
Get version details
Get version group details
List berries
List berry firmnesses
List berry flavors
List contest effects
List contest types
List encounter condition values
List encounter conditions
List encounter methods
List evolution chains
List evolution triggers
List generations
List item attributes
List item categories
List item fling effects
List item pockets
List items
List location areas
List locations
List pal park areas
List pokedexes
List regions
List super contest effects
List version groups
List versions
Execute a GraphQL query against PokéAPI
Why OpenAI Agents SDK?
The OpenAI Agents SDK auto-discovers all 49 tools from Poké through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns. chain multiple agents where one queries Poké, another analyzes results, and a third generates reports, all orchestrated through Vinkius.
- —
Native MCP integration via
MCPServerSse, pass the URL and the SDK auto-discovers all tools with full type safety - —
Built-in guardrails, tracing, and handoff patterns let you build production-grade agents without reinventing safety infrastructure
- —
Lightweight and composable: chain multiple agents and MCP servers in a single pipeline with minimal boilerplate
- —
First-party OpenAI support ensures optimal compatibility with GPT models for tool calling and structured output
Poké in OpenAI Agents SDK
Poké and 4,000+ other MCP servers. One platform. One governance layer.
Teams that connect Poké to OpenAI Agents SDK through Vinkius don't need to source, host, or maintain individual MCP servers. Every tool call runs inside a hardened runtime with credential isolation, DLP, and a signed audit chain.
Raw MCP | Vinkius | |
|---|---|---|
| Server catalog | Find and host yourself | 4,000+ managed |
| Infrastructure | Self-hosted | Sandboxed V8 isolates |
| Credential handling | Plaintext in config | Vault + runtime injection |
| Data loss prevention | None | Configurable DLP policies |
| Kill switch | None | Global instant shutdown |
| Financial circuit breakers | None | Per-server limits + alerts |
| Audit trail | None | Ed25519 signed logs |
| SIEM log streaming | None | Splunk, Datadog, Webhook |
| Honeytokens | None | Canary alerts on leak |
| Custom domains | Not applicable | DNS challenge verified |
| GDPR compliance | Manual effort | Automated purge + export |
Why teams choose Vinkius for Poké in OpenAI Agents SDK
The Poké MCP Server runs on Vinkius-managed infrastructure inside AWS — a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts. All 49 tools execute in hardened sandboxes optimized for native MCP execution.
Your AI agents in OpenAI Agents SDK only access the data you authorize, with DLP that blocks sensitive information from ever reaching the model, kill switch for instant shutdown, and up to 60% token savings. Enterprise-grade infrastructure, zero maintenance.

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
How Vinkius secures
Poké for OpenAI Agents SDK
Every tool call from OpenAI Agents SDK to the Poké MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
How can I find the specific details of a berry by its name?
Use the get_berry tool and provide the name (e.g., 'cheri'). The agent will return its growth time, max harvest, size, and smoothness.
Can I list all the different ways a Pokémon can be encountered?
Yes, use the list_encounter_methods tool. It provides a paginated list of all methods like 'walk', 'old-rod', or 'surf' used in the games.
Is it possible to check the effects of Pokémon Contests?
Absolutely. You can use list_contest_effects to see available effects or get_contest_effect with a specific ID to see the detailed appeal and jam metadata.
How does the OpenAI Agents SDK connect to MCP?
Use MCPServerSse(url=...) to create a server connection. The SDK auto-discovers all tools and makes them available to your agent with full type information.
Can I use multiple MCP servers in one agent?
Yes. Pass a list of MCPServerSse instances to the agent constructor. The agent can use tools from all connected servers within a single run.
Does the SDK support streaming responses?
Yes. The SDK supports SSE and Streamable HTTP transports, both of which work natively with Vinkius.
MCPServerStreamableHttp not found
Ensure you have the latest version: pip install --upgrade openai-agents
Agent not calling tools
Make sure your prompt explicitly references the task the tools can help with.
Explore More MCP Servers
View all →
Open Food Facts API
4 toolsSearch food products — audit nutrition, barcode, and categories via AI.

Shortcut
7 toolsEquip your AI agent to radically manage your Shortcut workspace. Search stories, track epics and iterations, fetch team members, and audit workflows from your IDE.

Mattermost (Secure Team Collaboration)
10 toolsManage team collaboration via Mattermost — send messages, search channels, and audit team activities.

Webflow
8 toolsDesign and build professional websites visually with a no-code platform that generates clean, production-ready HTML and CSS.
