How to Use the Crystal Matcher MCP in Vercel AI SDK

Q: Can I use Crystal Matcher with Vercel AI SDK in a multi-step chat?

Yep. Your agent can chain calls, starting with querycrystalsbyintent and then following up by using findcrystalsbychakra. The user sees the full process unfold as your client fetches data.

Show your users crystal recommendations live with Vercel AI SDK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Crystal Matcher MCP to Vercel AI SDK

Create your Vinkius account to connect Crystal Matcher 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 Crystal Matcher with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Match crystals by emotional intent

If the user just says they need 'calmness,' don't make them guess. Your agent starts by using `query_crystals_by_intent` to narrow down options based on a spiritual or emotional goal. Then, you can refine that list immediately with tools like `find_crystals_by_chakra`. This means the user sees the results streaming in real-time as your client filters out crystals that don't align with their specific energy centers.

Filter by crystal element

Sometimes, the vibe isn't enough; you need a physical match. Using `filter_crystals_by_element` lets your agent narrow results based on things like fire or water. When that list is done, you can always follow up with `get_crystal_details`. This gives the end user the full write-up—the crystal's history, how to care for it, and what makes it unique. It’s all visible right in the stream.

Build a multi-step matching experience

Your agent can handle complex user journeys without breaking stride. Start by asking the user's primary goal using `query_crystals_by_intent`, and then build out secondary constraints like specific elemental needs. This combination ensures that even if the initial search is vague, your client provides a structured path to actionable advice, all displayed live in the browser.

Setup guide

Set up Crystal Matcher 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 Crystal Matcher 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 Crystal Matcher 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 Crystal Matcher. 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 Crystal Matcher 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 Crystal Matcher MCP in Vercel AI SDK

The MCP executes inside your streaming endpoint. Your agent calls tools, and the resulting data immediately streams back to your UI layer. This makes the crystal recommendation process feel instant for the user.

Yep. Your agent can chain calls, starting with `query_crystals_by_intent` and then following up by using `find_crystals_by_chakra`. The user sees the full process unfold as your client fetches data.

This MCP handles crystal catalog data, including details about elements and chakras. Since it's a read-only operation against a structured database, no personal user data is touched by the server.

Since results stream directly into your frontend, you don't wait for a massive JSON blob. Your client handles data chunks as they arrive, making the experience feel quick even when there are many options.

Absolutely. The MCP runs in an isolated sandbox environment on Vinkius, meaning every tool call is secure and audited. Your connection stays clean no matter how complex the matching gets.

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