How to Use the Contentful MCP in Vercel AI SDK

Q: How do I pass Contentful tools to streamText in Vercel AI SDK?

Install @ai-sdk/mcp and instantiate the client. Pass mcpClient.tools() directly into the tools parameter of your streamText call to let your agent call tools like listentries and createentry in real time. Remember to run await mcpClient.close() when the edge execution finishes.

Q: How does the agent know which Contentful space to write to?

The agent uses listspaces and listenvironments to find the correct target. It inspects the available options and selects the correct IDs before executing any write operations like createentry.

Let your Vercel AI SDK agents query, edit, and publish Contentful content directly inside your live streaming frontend.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Contentful MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Real-time content editing in your UI

When your users ask your Vercel AI SDK agent to update a blog post, they don't want to wait for a spinning wheel. By feeding `update_entry` and `publish_entry` directly into your stream, the raw JSON modifications render instantly on the screen as the agent runs. You get immediate feedback loops. The agent pulls the existing structure with `get_content_type` and applies edits on the edge, keeping the React or Next.js UI snappy without blocking the main thread.

Direct space navigation via MCP Server

Stop hardcoding content IDs into your edge functions. This MCP Server lets your Vercel AI SDK client inspect your entire CMS setup dynamically by calling `list_spaces` and `list_environments` on the fly. The agent figures out where the content belongs, queries the right space, and pulls the correct schema. This means your Next.js application adapts automatically when marketing adds a new locale or environment in Contentful.

Live asset and draft discovery

Your streaming interface can now show media assets as they are being selected by the agent. By hooking `list_assets` and `list_entries` into your `streamText` tools array via our MCP connection, the UI displays draft content and images the second the agent finds them. Users can approve draft entries before they go live. The agent handles the lookup, fetches the specific draft using `get_entry`, and outputs the preview data directly into your React components.

Setup guide

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

Install `@ai-sdk/mcp` and instantiate the client. Pass `mcpClient.tools()` directly into the `tools` parameter of your `streamText` call to let your agent call tools like `list_entries` and `create_entry` in real time. Remember to run `await mcpClient.close()` when the edge execution finishes.

Yes, because the server handles authentication at the proxy layer. Your Vercel AI SDK code just invokes `publish_entry` or `unpublish_entry` without exposing your master management tokens to the browser.

Absolutely. The client connects via lightweight HTTP transport, meaning your Vercel AI SDK edge functions won't hit cold start bottlenecks or size limits while running `get_content_type`.

The agent uses `list_spaces` and `list_environments` to find the correct target. It inspects the available options and selects the correct IDs before executing any write operations like `create_entry`.

Your raw entries, space structures, and asset metadata pass through a secure, ephemeral V8 sandbox. No draft content or administrative payloads are stored on the proxy, keeping your headless CMS data completely isolated.

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