How to Use the DocsGenFlow MCP in Vercel AI SDK

Q: How do I handle authentication for DocsGenFlow within the Vercel AI SDK?

You configure the createMCPClient function with an HTTP transport pointing to your Vinkius endpoint token. The MCP setup routes all tool calls, like listhistory, through this single authenticated gateway automatically.

Q: How does DocsGenFlow stream template fields back to the Vercel AI SDK UI?

The SDK captures the tool output from gettemplate and streams it as a structured JSON chunk. Your React components can parse this stream in real-time to render input fields before the full document generation starts.

Connect the DocsGenFlow MCP Server to your Vercel AI SDK project for live document streaming.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect DocsGenFlow MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream live status checks in Vercel AI SDK

Your users hate waiting around for a slow PDF to compile. When you call `check_docsgenflow_status` through this Vercel AI SDK setup, the connection state renders live in your UI, giving users immediate feedback. This setup lets you run heavy document generation on Edge Functions without blocking the main browser thread. The client handles the background handshake, so you can execute `get_account` or check active limits without writing custom loading states.

Render template lists directly in React components

Populating a dropdown menu with your document layouts shouldn't require a complex state machine. By passing the `list_templates` tool directly to `streamText`, the Vercel AI SDK lists every template on your screen as the model discovers them. Once the user selects a template, your agent can call `get_template` to pull the exact merge fields required. This means your UI adapts on the fly to whatever fields the selected template needs, without hardcoded forms.

Generate and download PDFs on the Edge

Passing raw JSON data into `generate_document` triggers the rendering engine and returns file metadata instantly. Because this MCP Server runs in an isolated sandbox, your Edge Functions stay lightweight and secure. To let users grab their files, the agent calls `download_document` to fetch the file bytes. You can feed this stream directly to a browser download trigger, keeping the entire file-generation cycle inside your Vercel AI SDK interface.

Setup guide

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

You configure the `createMCPClient` function with an HTTP transport pointing to your Vinkius endpoint token. The MCP setup routes all tool calls, like `list_history`, through this single authenticated gateway automatically.

Yes, this MCP Server is fully compatible with Edge environments. You can run tools like `generate_document` directly inside Edge routes because the heavy rendering happens on the isolated Vinkius servers, not your local serverless instance.

The SDK captures the tool output from `get_template` and streams it as a structured JSON chunk. Your React components can parse this stream in real-time to render input fields before the full document generation starts.

You should set a standard timeout on your stream configuration. If `generate_document` takes too long, the SDK throws an error that you can catch in your frontend to suggest running `check_docsgenflow_status` to verify API health.

Your sensitive JSON merge fields and template data are processed within an ephemeral V8 sandbox. Once the PDF is compiled and you run `download_document`, the temporary data is wiped from the execution environment to ensure compliance.

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