How to Use the HotDocs MCP in Vercel AI SDK

Q: How do I list HotDocs templates in a Vercel AI SDK project?

Call listtemplatepackages using the SDK's generateText or streamText functions. This returns the complete list of template IDs and names directly to your agent. From there, you can pass the chosen ID to createworkitem to start the assembly process.

Q: How do I download the final generated document?

Once completeassembly finishes, your agent calls listdocuments to get the file ID. Then, it uses getdocumentcontent to retrieve the PDF or Word document stream and passes the download URL straight to your frontend.

Assemble HotDocs legal agreements in real-time and stream the generation status directly to your React frontend 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 HotDocs MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream HotDocs templates live with Vercel AI SDK

The `list_template_packages` tool fetches your active document templates from HotDocs Advance so your Vercel AI SDK client can render them instantly. Instead of waiting for a slow backend load, your React frontend receives the template structural data chunk by chunk as the agent discovers what forms are available. This MCP server lets your frontend display real-time template structural data chunk by chunk as the Vercel AI SDK agent discovers what forms are available. Once users select a form, the agent calls `get_template_package` to inspect the fields and build the input form on the fly without manual coding.

Real-time XML answer validation in the browser

The `update_answers` tool pushes user inputs directly into the active HotDocs work item using the platform's native XML schema. Your Vercel AI SDK agent updates the session state incrementally, sending raw XML data over Edge Functions to keep the UI highly responsive. To keep the user from submitting broken forms, the agent uses `get_unanswered_variables` to check for missing fields before assembling the file. The missing variables stream straight to your React components so users know exactly what to fix.

Instant document assembly feedback

The `complete_assembly` tool triggers the final document generation engine directly from your Vercel AI SDK stream. Instead of a blank loading screen, the agent streams the assembly progress and immediately calls `list_documents` to show the final files. Users get their download links instantly as the agent fetches the file payload via `get_document_content`. This is how you build a fast, responsive document generation portal on the Edge.

Setup guide

Set up HotDocs 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 HotDocs 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 HotDocs 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 HotDocs Advance. 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 HotDocs 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 HotDocs MCP in Vercel AI SDK

Call `list_template_packages` using the SDK's `generateText` or `streamText` functions. This returns the complete list of template IDs and names directly to your agent. From there, you can pass the chosen ID to `create_work_item` to start the assembly process.

Yes, the agent generates the required XML structure and passes it to `update_answers`. You don't have to write XML parsers yourself. The agent reads the schema rules from `get_template_package` and formats the user's inputs to match.

Yes, this HotDocs MCP Server runs on Vinkius's hosted infrastructure, meaning your Vercel AI SDK code stays lightweight and edge-compatible. You only need to make standard HTTP calls to the managed endpoint, avoiding heavy local dependencies.

Once `complete_assembly` finishes, your agent calls `list_documents` to get the file ID. Then, it uses `get_document_content` to retrieve the PDF or Word document stream and passes the download URL straight to your frontend.

Your XML answers and generated PDF documents never touch Vinkius disks. The server runs in an ephemeral V8 sandbox that processes the data in memory and forwards it directly to HotDocs Advance. Your credentials are encrypted and scoped only to your active session.

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