Vinkius
Sensible logo
Vinkius
Vinkius runs on Vercel AI SDK

How to Use the Sensible MCP in Vercel AI SDK

Pipe structured PDF data using the Sensible MCP Server and Vercel AI SDK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

Sensible MCP on Cursor AI Code Editor MCP Client Sensible MCP on Claude Desktop App MCP Integration Sensible MCP on OpenAI Agents SDK MCP Compatible Sensible MCP on Visual Studio Code MCP Extension Client Sensible MCP on GitHub Copilot AI Agent MCP Integration Sensible MCP on Google Gemini AI MCP Integration Sensible MCP on Lovable AI Development MCP Client Sensible MCP on Mistral AI Agents MCP Compatible Sensible MCP on Amazon AWS Bedrock MCP Support
MCP Servers — Included with Plan
Vinkius runs on Vercel AI SDK

Connect Sensible MCP to Vercel AI SDK

Create your Vinkius account to connect Sensible to Vercel AI SDK — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Key Capabilities

Zero-delay document parsing in Vercel AI SDK

Your users hate loading spinners. When they drop a PDF into your app, this MCP Server lets your agent immediately trigger `extract_sync` to grab raw data. Instead of waiting for a slow backend job to complete, the Vercel AI SDK streams the parsed fields directly onto the screen as they are identified. You build this by pairing `extract_sync_with_config` with streamText. The agent reads the incoming file bytes, matches them against your document schemas, and feeds the resulting JSON chunks straight into your UI components in real time.

Instant schema creation for Next.js forms

Stop writing manual form parsers for random tax documents or invoices. This integration lets your agent call `create_document_type` and `create_configuration` on the fly when a user uploads an unfamiliar layout. The agent defines the target schema, registers the new type, and prepares the parser without a single redeploy. Once the configuration is active, you can call `publish_configuration` to push it to production immediately. Your Vercel AI SDK application then handles future uploads of that document type instantly, bypassing manual mapping code entirely.

On-demand spreadsheet generation at the edge

Running heavy data conversion in Edge Functions used to be a pain. By offloading the heavy lifting to this MCP Server, your agent can call `generate_csv` or `generate_excel` to bundle parsed document data into downloadable files without exhausting your Vercel execution limits. The agent coordinates the export by fetching previous document runs with `list_extractions` and compiling them directly. Your users get their spreadsheets in seconds, and your edge middleware stays light and fast.

Setup guide

Set up Sensible 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. 1

    Install dependencies

    Run npm install ai @modelcontextprotocol/sdk plus your preferred model provider (e.g. @ai-sdk/openai).

  2. 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. 3

    Discover and use tools

    Call mcpClient.tools() to auto-discover all Sensible tools. Pass them directly to generateText() or streamText() — no manual schema definitions needed.

  4. 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 Sensible transactions",
});

console.log(text);
await mcpClient.close();

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Sensible. 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.

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 Sensible MCP in Vercel AI SDK

For files over a few megabytes, do not send raw bytes through the edge. Have your agent call `generate_upload_url` to get a pre-signed S3 link, upload the PDF directly from the browser, and then parse it using `extract_from_url`.
Yes. You can invoke `classify_sync` inside your streamText tool call to identify the document type instantly. The Vercel AI SDK then streams the classification result to your UI, letting the user know exactly what kind of form they uploaded.
Your agent uses `update_configuration` to tweak extraction rules based on user feedback. Because the Vercel AI SDK connects directly to the MCP Server, these updates apply instantly without requiring you to rebuild or redeploy your Next.js application.
The agent can call `list_configuration_versions` to inspect older parsing rules. If a layout breaks, the agent can rollback or update the rules using `publish_configuration` to keep your production pipeline running.
Your documents are processed in secure, ephemeral V8 sandboxes. Your raw PDF files and extracted data payloads never persist on our servers; they are discarded immediately after the execution of your tool calls.

Start using the Sensible MCP today

We host it, we monitor it, we maintain it. You just paste one token.

Built & Managed by Vinkius 30s setup 37 tools

We've already built the connector for Sensible. Just plug in your AI agents and start using Vinkius.

No hosting. No infrastructure. No complex setup.
All 37 tools are live and waiting. You're up and running in seconds.

Vinkius runs on Claude Claude
Vinkius runs on ChatGPT ChatGPT
Vinkius runs on Cursor Cursor
Vinkius runs on Gemini Gemini
Vinkius runs on Windsurf Windsurf
Vinkius runs on VS Code VS Code
Vinkius runs on JetBrains JetBrains
Vinkius runs on Vercel Vercel
+ other MCP clients

Vinkius gives your AI agents access to the full catalog of app connectors, all fully managed, secure, and enterprise-ready. One subscription, every tool you need.

Zero hosting required Full MCP catalog included Enterprise-grade security Auto-updated by Vinkius

Built, hosted, and secured by Vinkius. You just connect and go.