How to Use the Adobe Sign MCP in Vercel AI SDK

Q: How do I set up Adobe Sign with the Vercel AI SDK?

Install @ai-sdk/mcp and call createMCPClient with your Vinkius endpoint. Pass the tools directly into streamText to let your agent call createagreement during a live chat session.

Q: Can the Vercel AI SDK stream the PDF files from Adobe Sign?

Yes. The agent uses getagreementcombineddocument to fetch the completed PDF. The Vercel AI SDK streams the download link or file metadata directly to your frontend components.

Q: How does Vercel AI SDK handle transient documents in Adobe Sign?

Your agent calls createtransientdocument to upload the raw file, which stays active for 7 days. Once uploaded, the SDK passes the resulting ID to createagreement to finish the signature request.

Q: How do I close the MCP connection in my Next.js API route?

Always call mcpClient.close() after your streamText or generateText function finishes execution. This prevents memory leaks and hanging connections in your serverless edge functions.

Send Adobe Sign agreements and stream live audit trails directly into your React or Next.js app using the 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 Adobe Sign MCP to Vercel AI SDK

Create your Vinkius account to connect Adobe Sign 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 Adobe Sign with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Generate and send agreements live inside your UI

The `create_agreement` tool lets your AI client initiate e-signature requests directly from a user prompt. Because you use the Vercel AI SDK, the agreement status and recipient details stream into your React frontend in real-time without making the user wait for a page reload. You feed transient files to the API using `create_transient_document` first, then immediately pass that document ID to the agreement creator. The entire document generation process happens on the edge, keeping your Next.js application fast and responsive.

Stream completed PDFs and audit trails to users

The `get_agreement_combined_document` tool pulls the fully executed PDF file as soon as all parties sign. Your AI client fetches this file on demand, allowing your frontend to display or download the completed document instantly. For compliance tracking, the `get_agreement_audit_trail` tool retrieves the official execution history. Your Vercel AI SDK setup streams this timeline directly to your user interface, giving your customers immediate proof of signature validity.

Track Adobe Sign status changes via Vercel AI SDK

The `create_webhook` tool registers real-time event listeners for document status changes. Your AI client configures these webhooks automatically, so your application knows the exact moment a client signs or rejects a contract. Combining this with `list_agreements` lets your interface show a live, updating dashboard of pending signatures. You configure the MCP client once, and your edge functions handle the background polling and event updates.

Setup guide

Set up Adobe Sign 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 Adobe Sign 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 Adobe Sign 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 Adobe Sign. 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 Adobe Sign 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 Adobe Sign MCP in Vercel AI SDK

Install `@ai-sdk/mcp` and call `createMCPClient` with your Vinkius endpoint. Pass the tools directly into `streamText` to let your agent call `create_agreement` during a live chat session.

Yes. The agent uses `get_agreement_combined_document` to fetch the completed PDF. The Vercel AI SDK streams the download link or file metadata directly to your frontend components.

Your agent calls `create_transient_document` to upload the raw file, which stays active for 7 days. Once uploaded, the SDK passes the resulting ID to `create_agreement` to finish the signature request.

Always call `mcpClient.close()` after your `streamText` or `generateText` function finishes execution. This prevents memory leaks and hanging connections in your serverless edge functions.

Your document payloads, transient files, and signer emails pass directly through an ephemeral, zero-trust V8 isolate sandbox. Vinkius never writes your PDF content or audit trails to persistent storage, ensuring absolute transit privacy.

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