How to Use the CurseForge MCP in Vercel AI SDK

Q: Can I render CurseForge mod descriptions as live markdown using the Vercel AI SDK?

Yes, the getmoddescription tool returns HTML which your React app can safely render or pass to the SDK's text generation tools. This lets you clean up messy formatting before displaying it.

Q: How do I close the CurseForge MCP Server connection in a Vercel AI SDK serverless function?

Always call mcpClient.close() at the end of your execution block. This prevents hanging HTTP connections in your Vercel serverless or edge environments.

Q: How do I get signed download links for specific mods?

Use the getmodfiledownloadurl tool to retrieve the direct, secure URL for any file. Your frontend can then present a direct download button to the user.

Feed real-time CurseForge mod data directly into your Next.js UI using the 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 CurseForge MCP to Vercel AI SDK

Create your Vinkius account to connect CurseForge 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 CurseForge with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Live CurseForge Mod Search via Vercel AI SDK

The `search_mods` tool lets your Next.js app query the CurseForge database instantly without building a custom backend search wrapper. Your interface streams live mod lists, categories, and download counts directly to the user's viewport. Because the Vercel AI SDK handles the streaming connection natively, users see mod cards populate as the model finds them. No annoying spinners while waiting for a massive payload to resolve.

On-Demand Mod Changelogs and Files

The `get_mod_file_changelog` tool fetches raw HTML update logs for specific game versions on the fly. You feed this data straight into your React components to show players exactly what changed in their Minecraft or WoW setups. Combine this with `get_mod_file` to display precise file sizes and compatible game versions. Your AI client pulls the data, formats it, and renders it on screen without page refreshes.

Instant Fingerprint Matching for Local Client Files

The `get_fingerprints_matches` tool identifies local game files by checking their unique hash values against the CurseForge database. This lets your web-based client scanner detect installed mods and flag updates. Since this MCP tool runs perfectly in edge functions, you execute these heavy hash-matching queries close to your players. It keeps the scanning interface fast and responsive.

Setup guide

Set up CurseForge 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 CurseForge 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 CurseForge 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 CurseForge. 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 CurseForge 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 CurseForge MCP in Vercel AI SDK

We manage the rate limits on our backend so your Next.js edge functions don't trigger blocks. You just call `search_mods` or `get_mod` through the MCP client, and we handle the traffic distribution.

Yes, the `get_mod_description` tool returns HTML which your React app can safely render or pass to the SDK's text generation tools. This lets you clean up messy formatting before displaying it.

Always call `mcpClient.close()` at the end of your execution block. This prevents hanging HTTP connections in your Vercel serverless or edge environments.

Use the `get_mod_file_download_url` tool to retrieve the direct, secure URL for any file. Your frontend can then present a direct download button to the user.

We process your mod file hashes and search queries in ephemeral V8 sandboxes. Your raw file fingerprints are never stored, logged, or shared with third parties.

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