How to Use the Docdown MCP in Vercel AI SDK

Q: How do I handle Docdown template updates in Vercel AI SDK?

Use listdoctemplates to fetch the latest layouts. Your AI client can query this MCP tool dynamically, meaning any template changes you make in your dashboard show up immediately in your Next.js application without a rebuild.

Q: Can Vercel AI SDK generate Docdown documents during a live stream?

Yes. The SDK triggers generatenewdocument mid-stream as soon as it gathers the required inputs. It then uses getdocumentstatus to poll the API and sends the final download link to the user.

Q: How does Vercel AI SDK discover required Docdown fields?

The agent calls gettemplatefieldschema to inspect the template structure. It parses the JSON schema and prompts the user for only the missing variables before calling the generation tool.

Build web apps that stream PDF generation in real-time by linking Vercel AI SDK to Docdown templates.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Docdown MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Instantly fetch Docdown templates on the Edge

`list_published_templates` pulls active document templates directly into your Edge Functions. This MCP Server tool gets the exact layout ID you need without hitting heavy database layers, keeping your Vercel AI SDK application fast. Your application receives the template list and passes it to the client side. By avoiding cold starts on Vercel, your user gets an immediate dropdown of available forms instead of watching a blank loading state.

Stream custom template fields straight to the UI

`get_template_field_schema` extracts the exact payload parameters your user needs to fill out. The AI client reads this schema and instantly renders the corresponding input fields in your React or Next.js frontend. This means you do not hardcode form components for every document type. When a user selects a template, the Vercel AI SDK streams the required field structure, letting the UI adapt on the fly.

Generate live PDFs using this Docdown MCP Server

`generate_new_document` triggers PDF creation using the user-provided data payload. Your AI client monitors the build process using `get_document_status` and feeds progress updates directly to the streaming UI. Instead of showing a static spinner, the Vercel AI SDK displays the live status of the document build. Once complete, the download URL appears instantly in the chat window.

Setup guide

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

Use `list_doc_templates` to fetch the latest layouts. Your AI client can query this MCP tool dynamically, meaning any template changes you make in your dashboard show up immediately in your Next.js application without a rebuild.

Yes. The SDK triggers `generate_new_document` mid-stream as soon as it gathers the required inputs. It then uses `get_document_status` to poll the API and sends the final download link to the user.

The agent calls `get_template_field_schema` to inspect the template structure. It parses the JSON schema and prompts the user for only the missing variables before calling the generation tool.

Look, if the API returns an error payload, your agent reads it directly. You can catch these exceptions in your route handler and stream a clean error message back to the frontend.

All document payloads and PDF metadata pass through an ephemeral MCP V8 sandbox on Vinkius. Your API keys are injected at the gateway level, so your raw credentials never touch the client browser or external LLM logs.

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