How to Use the Docupilot MCP in Vercel AI SDK

Q: How does Docupilot handle streaming statuses in Vercel AI SDK?

The agent uses getdocumentgenerationstatus inside a loop to poll Docupilot while streaming the progress token-by-token. Your UI displays live updates directly to the user instead of blocking the main thread.

Q: How do I map dynamic form fields using Docupilot and Vercel AI SDK?

You have your agent call gettemplateschema to inspect the template's structure. The Vercel AI SDK then uses that schema to generate a typed React form on the fly, ensuring zero data mismatch.

Q: Can the agent check our account limits before running a merge?

The agent calls getdocupilotaccountmetadata to verify your remaining document balance. If you are close to your limit, the agent alerts you before executing another merge.

Render real-time Docupilot PDF generation updates in your Next.js UI using 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 Docupilot MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Live template discovery in your web app

Your Vercel AI SDK client uses the MCP Server tool `list_docupilot_templates` to fetch your active layouts the moment a user starts a document draft. It feeds these directly into your Next.js frontend, letting users pick templates without waiting for a full page reload. By calling `search_docupilot_templates`, your Vercel AI SDK agent filters options on the fly as the user types. This keeps your Vercel AI SDK app fast since the LLM does the sorting before rendering the UI.

Dynamic schema validation for Edge Functions

The `get_template_schema` tool pulls the exact data structure required for a selected Docupilot template directly inside your Vercel AI SDK edge runtime. Your agent inspects this schema to build a dynamic form in your React interface instantly. To stop bad inputs before they hit your billing, your Vercel AI SDK agent runs `get_template_merge_field_audit` so you don't waste money on failed requests. This keeps your Vercel AI SDK pipeline clean and prevents broken document merges.

Real-time merge streaming via Vercel AI SDK

The `trigger_document_merge` tool initiates the Docupilot generation process, sending payload data straight from your Vercel AI SDK frontend. Instead of showing a static loading spinner, your Vercel AI SDK setup streams progress updates directly to the browser. While the Docupilot document renders, your Vercel AI SDK agent repeatedly calls `get_document_generation_status` to pull the latest PDF download URL. This MCP server integration ensures your users see their completed invoices or contracts appear on screen the millisecond they are ready.

Setup guide

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

The agent uses `get_document_generation_status` inside a loop to poll Docupilot while streaming the progress token-by-token. Your UI displays live updates directly to the user instead of blocking the main thread.

Yes, this MCP Server is fully compatible with edge runtimes. Your agent invokes `search_docupilot_templates` to query your document library directly from an edge route with minimal latency.

You have your agent call `get_template_schema` to inspect the template's structure. The Vercel AI SDK then uses that schema to generate a typed React form on the fly, ensuring zero data mismatch.

The agent calls `get_docupilot_account_metadata` to verify your remaining document balance. If you are close to your limit, the agent alerts you before executing another merge.

Your template schemas and raw merge data travel directly between your edge function and Docupilot over encrypted HTTPS connections. Vinkius runs this MCP Server in an isolated, ephemeral sandbox, ensuring your private payload data is never cached or stored on our hosting infrastructure.

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