How to Use the Gamma (AI Presentations) MCP in Vercel AI SDK

Q: How do I connect Gamma (AI Presentations) to the Vercel AI SDK?

Use createMCPClient with the HTTP transport URL. Pass the result to mcpClient.tools() and feed it into generateText. Always call mcpClient.close() when finished.

Q: How do I list existing decks using Gamma (AI Presentations) with Vercel AI SDK?

Ask your agent to find your files. It calls listgammas to pull the workspace inventory. The agent then formats that JSON into whatever UI component you built.

Build real-time presentation generators in your React apps with 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 Gamma (AI Presentations) MCP to Vercel AI SDK

Create your Vinkius account to connect Gamma (AI Presentations) 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 Gamma (AI Presentations) with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream slide generation directly to the UI

`create_gamma` builds presentations, documents, and webpages straight from a user prompt. Your Vercel AI SDK client streams the tool execution state straight to the frontend. Users watch the deck build itself live instead of staring at a static loading spinner. You just pass the MCP client tools into `streamText`. The user types a request, the edge function triggers the creation, and your React component renders the progress. No polling logic is required.

Manage workspace files from your Next.js app

`list_gammas` pulls the entire directory of existing decks directly into your application state. Developers can map these straight into a custom dashboard component. If a user needs to find a specific deck, the agent retrieves the list instantly. Fetching deep details happens through `get_gamma`. The agent reads the structure and content of a specific file. It then passes that data back to the user or uses it as context for the next chat interaction.

Edit and delete with Vercel AI SDK tools

`update_gamma` lets your agent modify existing presentations based on chat input. A user asks for a different color scheme or new slide content, and the agent executes the change. The UI updates immediately to reflect the new document state. Cleaning up is just as direct. `delete_gamma` removes unwanted drafts from the workspace. You wire this up to a simple confirmation button, and the agent handles the API interaction behind the scenes.

Setup guide

Set up Gamma (AI Presentations) 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 Gamma (AI Presentations) 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 Gamma (AI Presentations) 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 Gamma. 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 Gamma (AI Presentations) 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 Gamma (AI Presentations) MCP in Vercel AI SDK

Use `createMCPClient` with the HTTP transport URL. Pass the result to `mcpClient.tools()` and feed it into `generateText`. Always call `mcpClient.close()` when finished.

Yes. Because the SDK supports tool streaming, users see the progress of the presentation generation in real-time. You never have to write custom polling loops.

It does. The standard HTTP transports execute perfectly in edge environments. Your Next.js API routes stay fast and lightweight.

Ask your agent to find your files. It calls `list_gammas` to pull the workspace inventory. The agent then formats that JSON into whatever UI component you built.

Vinkius runs the server in an ephemeral V8 Isolate. Only the specific presentation text and workspace IDs you request pass through the connection. We drop the memory state entirely once the edge function closes the transport.

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