How to Use the Airparser MCP in Vercel AI SDK

Q: How do I configure the Airparser MCP Server with Vercel AI SDK?

Install @ai-sdk/mcp and instantiate the client using createMCPClient with your HTTP endpoint. Pass the tools directly into streamText to let your MCP agent parse documents. Always call mcpClient.close() when the session ends.

Q: Can I stream live extraction progress using Airparser on Vercel AI SDK?

Yes, you use parsedocumentsync to extract data and immediately stream the resulting JSON into your frontend. This avoids loading screens by letting Vercel AI SDK render the parsed fields as they arrive.

Q: How does Vercel AI SDK handle multiple Airparser inboxes?

Your agent runs listinboxes to find the correct target inbox. Once found, it uses getinboxschema to understand the structure before starting the document extraction.

Pipe parsed document data directly into your Next.js UI in real-time 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 Airparser MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Real-Time Document Parsing in Vercel AI SDK

The `parse_document_sync` tool extracts structured data from uploaded PDFs or emails and feeds it directly into your streaming UI. Instead of making your users stare at a blank loading spinner, you pipe the raw JSON payload straight into Vercel AI SDK's stream, rendering form fields as they populate. Your frontend triggers the extraction by calling the client tools array. When the extraction completes, you run `get_document_details` to verify the parsed fields against your React state before closing the connection with `mcpClient.close()`.

Dynamic Form Generation via MCP Server Schemas

The `get_inbox_schema` tool pulls the exact extraction fields defined in your Airparser inbox so your Vercel AI SDK app can build dynamic UI forms on the fly. You don't hardcode input fields; your Next.js app queries this MCP Server and renders matching React components instantly. Combined with `list_inboxes`, this lets users choose an inbox, see the required fields, and upload a document. The client processes the file and populates the UI using the exact structure returned by the server.

Automated Export Pipelines for Edge Functions

The `create_webhook` tool configures real-time document export destinations directly from your TypeScript edge route. You write a standard API route that listens for incoming Airparser events, instantly updating your Vercel AI SDK chat interface. If a user changes their export destination, your app calls `delete_webhook` to clean up old routes. It keeps your database clean and ensures your serverless functions only run when fresh document data arrives.

Setup guide

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

Install `@ai-sdk/mcp` and instantiate the client using `createMCPClient` with your HTTP endpoint. Pass the tools directly into `streamText` to let your MCP agent parse documents. Always call `mcpClient.close()` when the session ends.

Yes, you use `parse_document_sync` to extract data and immediately stream the resulting JSON into your frontend. This avoids loading screens by letting Vercel AI SDK render the parsed fields as they arrive.

Your agent runs `list_inboxes` to find the correct target inbox. Once found, it uses `get_inbox_schema` to understand the structure before starting the document extraction.

Yes, the server integration is fully compatible with Edge runtimes. Because it uses standard HTTP transport, you avoid cold starts and heavy node dependencies.

Your PDFs, emails, and images are processed securely by Airparser, and only the extracted structured JSON data returns to your Vercel deployment. Vinkius runs this MCP server in an isolated, zero-trust sandbox, ensuring your document payloads are never cached or exposed to third parties.

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