How to Use the GatherContent MCP in Vercel AI SDK

Q: Can I use GatherContent templates dynamically with Vercel AI SDK?

Yes. You call gettemplateschema to retrieve the field requirements, then pass those rules directly into your Vercel AI SDK system prompt. This ensures the model outputs JSON that fits your structured content fields perfectly.

Q: Do I need a separate backend to connect GatherContent to my Next.js app?

No. You can connect directly. Using createMCPClient from @ai-sdk/mcp, you point your Next.js API route straight to the hosted Vinkius endpoint, keeping your architecture entirely serverless.

Build real-time editorial tools that stream GatherContent updates directly into your Vercel AI SDK frontend.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect GatherContent MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream GatherContent updates via Vercel AI SDK

This MCP Server lets you feed live editorial changes from your GatherContent projects straight into your Next.js or React components. By running `get_item_content` inside your Vercel AI SDK stream, your users watch draft updates build in real-time without hitting a reload button. It bypasses the usual API latency by piping structured fields directly into the Vercel AI SDK rendering loop. You can build custom Next.js interfaces where writers watch their GatherContent text populate as the Vercel AI SDK generates it. The Vercel AI SDK uses `get_template_schema` to map fields instantly, ensuring that whatever the model outputs conforms directly to your predefined GatherContent fields before it updates.

Live project mapping inside Edge Functions

Deploy lightweight editorial tools that run on the edge using Vercel's infrastructure. By calling `list_content_projects` and `list_project_folders` within your Vercel AI SDK edge route, you fetch your GatherContent asset structure instantly. This setup keeps your bundle size small while keeping your editorial dashboard fast. Your Next.js application queries `list_content_templates` on demand, allowing your Vercel AI SDK client to adapt its generation style to match the current GatherContent folder's guidelines. It keeps your latency low and ensures you don't boot up heavy server instances just to check a project status.

Interactive state management for teams

Keep your editorial team updated by letting your Vercel AI SDK client manage GatherContent workflow transitions live. Using `list_workflow_statuses` paired with `update_content_item`, your application can transition drafts from 'writing' to 'review' as soon as the streaming generation completes. The Vercel AI SDK handles these transitions in the background, keeping the user interface perfectly synced with the actual database. This setup removes the need for manual status updates in the GatherContent dashboard. Your writers see the status badge flip colors on their Next.js screen the second the Vercel AI SDK finishes writing the final paragraph.

Setup guide

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

You can catch rate limit errors directly in your stream handlers. Since you run `update_content_item` within your Vercel AI SDK route, we recommend using standard Vercel edge middleware to throttle incoming requests or queue them before they hit the server endpoint.

Yes. You call `get_template_schema` to retrieve the field requirements, then pass those rules directly into your Vercel AI SDK system prompt. This ensures the model outputs JSON that fits your structured content fields perfectly.

The server doesn't stream character-by-character into the database, but it lets your Vercel AI SDK stream the generation to the user's screen first, then calls `update_content_item` to save the completed text once the stream finishes.

No. You can connect directly. Using `createMCPClient` from `@ai-sdk/mcp`, you point your Next.js API route straight to the hosted Vinkius endpoint, keeping your architecture entirely serverless.

Your draft content, folder structures, and user profiles accessed via `get_my_identity` never persist on our servers. Vinkius runs this connector inside a secure, ephemeral V8 isolate sandbox, executing the API requests directly to GatherContent and discarding the runtime memory immediately after.

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