How to Use the Agility CMS MCP in Vercel AI SDK

Q: Can Vercel AI SDK render Agility CMS media?

Yes. The getmediagallery tool returns photo mappings from your CMS. Your Next.js frontend can take those URLs from the stream and render them inside standard image components.

Connect Agility CMS to Vercel AI SDK and stream content data directly into your React or Next.js frontends without loading spinners.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Agility CMS MCP to Vercel AI SDK

Create your Vinkius account to connect Agility CMS 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 Agility CMS with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream Agility CMS MCP Server data to React

`list_content_items` feeds your Vercel AI SDK generation functions with live headless CMS data. You call the tool, and the client streams those blog posts or author profiles straight into your Next.js frontend. Users see the text appear instantly instead of staring at a blank screen. Getting specific pages works the exact same way. `get_page_layout` grabs the structural modules of a single page while the UI renders it piece by piece. You skip the heavy static builds and let the AI build dynamic views on the fly.

Fetch delta updates for live interfaces

`sync_incremental_items` pulls only what changed since your last token sync. Your agent grabs the latest data and pushes it through the streamable HTTP transport. This keeps your edge functions fast because they aren't pulling the entire database every time someone asks a question. Searching large reference lists happens instantly. `search_content_reference` accepts exact keywords to find targeted content inside the CMS. The Vercel AI SDK takes that raw JSON and formats it into markdown or custom React components via tool calls.

Map site architecture dynamically

`get_site_tree` exposes the nested sitemap architecture of any digital channel directly to your agent. Your AI client reads the hierarchy and builds navigation menus in real-time. It knows exactly where every page lives. Flat routing needs are handled just as easily. `get_site_flat_router` dumps the exact list of all CMS routes. You pass this into your prompt context, and the AI knows exactly which URLs are valid before generating links for the user.

Setup guide

Set up Agility CMS 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 Agility CMS 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 Agility CMS 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 Agility CMS. 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 Agility CMS 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 Agility CMS MCP in Vercel AI SDK

Install the @ai-sdk/mcp package and initialize it with createMCPClient. Point the HTTP transport URL to your Vinkius endpoint. Pass the resulting tools into your streamText function.

Yes. The get_media_gallery tool returns photo mappings from your CMS. Your Next.js frontend can take those URLs from the stream and render them inside standard image components.

Vinkius hosts the server externally, so your edge functions just make standard HTTP requests. You don't install heavy dependencies in your Vercel project. Just call the endpoint and stream the result.

Vinkius manages the actual CMS credentials inside a V8 Isolate Sandbox. Your application only needs the single endpoint token provided by the marketplace. Pass that token in your transport headers.

Your article bodies, page layouts, and author profiles remain entirely secure. Vinkius spins up an ephemeral sandbox for every request. Zero data persists on our infrastructure after the HTTP response closes.

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