How to Use the DocuSign MCP in Vercel AI SDK

Q: Can I use Vercel AI SDK to cancel an envelope in DocuSign?

Yes, you feed the voidenvelope tool into your model configuration. When the user tells your UI to cancel a contract, the SDK invokes the tool and updates your frontend state to show the voided status instantly.

Q: How do I pull document folders using Vercel AI SDK and DocuSign?

You call listfolders through the MCP tool calling mechanism. The returned folder structure streams directly into your UI, allowing your model to render file trees or document lists without lag.

Q: What happens if a recipient fails to sign a sent document?

Your model can call listrecipients to see who is holding up the process. You can then trigger a follow-up action or display the pending signer's email directly in your application dashboard.

Build live-updating signature portals in Next.js by streaming DocuSign status updates directly into Vercel AI SDK frontends.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect DocuSign MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream real-time signing links with `get_signing_url`

The `get_signing_url` tool fetches an active signing link from DocuSign so your React components can render it instantly. Instead of making your users wait for a backend redirect, Vercel AI SDK streams the generated token straight to the client-side UI. Your interface gets the raw JSON payload containing the URL without triggering a full page reload. You get to render a clean, clickable button the millisecond DocuSign generates the link.

Track signature status live using this MCP Server

The `get_envelope` tool pulls current signature metadata from DocuSign to update your interface state. This MCP Server lets your agent check if a client signed a document while they are actively chatting with your app. By feeding this data into Vercel AI SDK, your chat interface updates its state in real-time. The user sees a visual confirmation bubble change from pending to completed without clicking a manual refresh button.

Render template options directly with `list_templates`

The `list_templates` tool retrieves your pre-built DocuSign layouts so your Next.js frontend can show them in a dropdown. Your agent reads the template list through this MCP connection and dynamically builds UI components based on your active contract types. Passing this raw template list to the Vercel AI SDK lets you build interactive document builders. Users pick a template in chat, and the agent instantly populates the required fields for their signature request.

Setup guide

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

The server passes raw envelope metadata directly to the chat stream. Your agent calls `send_envelope` and immediately pushes the transaction ID to your React component, letting you show progress indicators while DocuSign processes the files.

Yes, you feed the `void_envelope` tool into your model configuration. When the user tells your UI to cancel a contract, the SDK invokes the tool and updates your frontend state to show the voided status instantly.

You call `list_folders` through the MCP tool calling mechanism. The returned folder structure streams directly into your UI, allowing your model to render file trees or document lists without lag.

Your model can call `list_recipients` to see who is holding up the process. You can then trigger a follow-up action or display the pending signer's email directly in your application dashboard.

No. Your envelope contents, recipient emails, and signing URLs remain private because they bypass external storage. The Vinkius MCP gateway runs the underlying connector inside an isolated, ephemeral V8 container, ensuring your legal documents are never cached or stored on our servers.

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