How to Use the Sproof MCP in Vercel AI SDK

Q: How does Sproof and ai-sdk handle document listing?

You list documents using the listdocuments tool. This returns a paginated list of file records that you can then display in your component. It's reliable for building an inventory view because it handles both successful pagination and potential errors cleanly.

Q: What data does Sproof and ai-sdk expose about signature requests?

The getsignaturerequest tool returns the full details of a specific signing session. This includes metadata, current status, and who is assigned to sign. You can also get an overview of everything with listsignaturerequests, which shows all pending or completed workflows.

Q: How can Sproof and ai-sdk track changes?

You use the listaudittrail tool to pull the complete history for any signature request. This log tracks every action taken, which is critical for compliance views. It’s a straightforward mechanism that gives you immutable proof of when things happened.

Q: Does Sproof and ai-sdk support canceling requests?

Yep. If a request needs to be halted, the cancelsignaturerequest tool lets your agent stop a pending workflow. This is useful if the underlying document changes before signing begins. You just pass the ID, and it handles the termination for you.

Q: What data type does Sproof and ai-sdk touch regarding privacy?

This server touches Documents metadata. The getdocument tool fetches details about files, which is the primary piece of sensitive information your application needs to display.

Stream real-time signature status updates directly into your React/Next.js frontend using 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 Sproof MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Monitor Request Status

To check the current state of a signing workflow, call `get_signature_request` or view all active sessions with `list_signature_requests`. This lets your agent display changes immediately—the user sees data appear live, not after a loading spinner. You can also get details on any single document using `get_document`, which is key when building interactive forms. It's how you keep the UI in sync with what Sproof has processed.

Manage User Contacts

Need to add a new person for signing? Use `create_contact` to register them first. You can then list all known users via `list_contacts`. This ensures your user-facing product always uses the most current contact data. When you're ready, the `create_signature_request` tool lets you initiate the process by passing required JSON payloads directly into the stream.

Review Documents and History

Your agent can fetch a list of all documents using `list_documents`, giving your UI an immediate inventory. For deeper context, calling `get_document` retrieves specific metadata you need to display. If something goes wrong or needs tracking, the `list_audit_trail` tool provides the history needed for compliance views within your application.

Setup guide

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

You list documents using the `list_documents` tool. This returns a paginated list of file records that you can then display in your component. It's reliable for building an inventory view because it handles both successful pagination and potential errors cleanly.

The `get_signature_request` tool returns the full details of a specific signing session. This includes metadata, current status, and who is assigned to sign. You can also get an overview of everything with `list_signature_requests`, which shows all pending or completed workflows.

You use the `list_audit_trail` tool to pull the complete history for any signature request. This log tracks every action taken, which is critical for compliance views. It’s a straightforward mechanism that gives you immutable proof of when things happened.

Yep. If a request needs to be halted, the `cancel_signature_request` tool lets your agent stop a pending workflow. This is useful if the underlying document changes before signing begins. You just pass the ID, and it handles the termination for you.

This server touches **Documents** metadata. The `get_document` tool fetches details about files, which is the primary piece of sensitive information your application needs to display.

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