How to Use the Harry Potter API MCP in Vercel AI SDK

Q: How do I connect the Harry Potter API to Vercel AI SDK?

Install @ai-sdk/mcp and initialize your client with createMCPClient. Point the HTTP transport to the provided Vinkius endpoint. Pass the tools directly into your streamText call.

Q: Can Vercel AI SDK stream the Harry Potter API spell list?

Yes. When the agent calls getspells, the SDK streams the spell names and descriptions back to your frontend as they resolve. Your users see the text appear instantly.

Q: What data do I get from the staff endpoint?

The getstaff tool returns names, houses, roles, and actor names for Hogwarts teachers. You can use this to build faculty directories in your Vue or Svelte apps.

Stream Harry Potter API data directly into your React frontends using the Vercel AI SDK and this MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Harry Potter API MCP to Vercel AI SDK

Create your Vinkius account to connect Harry Potter API to Vercel AI SDK and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Harry Potter API with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream Hogwarts Rosters Live

The `get_house_characters` tool pulls complete rosters for Gryffindor, Slytherin, Ravenclaw, or Hufflepuff. You pass the house name, and the server returns the character names, actors, and patronuses. Because you build with Vercel AI SDK, this data streams straight into your user interface. Your app renders the student lists row by row in real-time instead of making users stare at a loading spinner.

Build Spell Discovery UIs

The `get_spells` tool fetches the exact name, type, and effect description for every incantation in the database. Your agent can search for specific hexes or charms based on user prompts. Tie this to a Next.js search component. When a user asks how to disarm an opponent, the client calls the tool and immediately streams the Expelliarmus details back to the chat window.

Vercel AI SDK MCP Server Integration

The `get_character` and `get_all_characters` tools handle deep dives into individual character backgrounds. You get the species, ancestry, and alive status for anyone in the universe. Setup takes minutes with `@ai-sdk/mcp`. You call `createMCPClient`, map the transport URL, and pass the resulting tools array into `streamText` to start rendering live wizarding world data.

Setup guide

Set up Harry Potter API MCP in Vercel AI SDK

Prerequisites

Node.js 18+ and a TypeScript project
ai + @modelcontextprotocol/sdk packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies

Run npm install ai @modelcontextprotocol/sdk plus your preferred model provider (e.g. @ai-sdk/openai).
2

Create the Streamable HTTP transport

Use StreamableHTTPClientTransport with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and use tools

Call mcpClient.tools() to auto-discover all Harry Potter API tools. Pass them directly to generateText() or streamText() — no manual schema definitions needed.
4

Works with any model provider

Swap openai("gpt-4o") for any AI SDK provider — Anthropic, Google, Mistral. The MCP tools work identically across all supported models.

index.ts

import { experimental_createMCPClient as createMCPClient } from "ai";
import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp";
import { generateText } from "ai";
import { openai } from "@ai-sdk/openai";

const transport = new StreamableHTTPClientTransport(
  new URL("https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
);

const mcpClient = await createMCPClient({ transport });
const tools = await mcpClient.tools();

const { text } = await generateText({
  model: openai("gpt-4o"),
  tools,
  prompt: "List recent Harry Potter API transactions",
});

console.log(text);
await mcpClient.close();

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by HP-API. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Harry Potter API now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Harry Potter API MCP in Vercel AI SDK

Install `@ai-sdk/mcp` and initialize your client with `createMCPClient`. Point the HTTP transport to the provided Vinkius endpoint. Pass the tools directly into your `streamText` call.

Yes. When the agent calls `get_spells`, the SDK streams the spell names and descriptions back to your frontend as they resolve. Your users see the text appear instantly.

The `get_staff` tool returns names, houses, roles, and actor names for Hogwarts teachers. You can use this to build faculty directories in your Vue or Svelte apps.

You handle caching at the edge or application layer. The MCP Server fetches fresh data on every request, so you should cache heavy responses like `get_all_characters` in your Next.js route handlers.

This server only reads public wizarding world lore, specifically character traits, house affiliations, and spell descriptions. It processes zero personally identifiable information from your end users. The V8 Isolate Sandbox destroys the environment immediately after the request finishes.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript