How to Use the Sansan MCP in Vercel AI SDK

Q: How do I handle large contact lists without breaking the UI?

Use listbizcards with strict pagination limits in your prompt instructions. The language model will fetch manageable chunks, keeping the React render cycle smooth.

Stream digitized business card data directly into your React frontends using the Vercel AI SDK and the Sansan MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Sansan MCP to Vercel AI SDK

Create your Vinkius account to connect Sansan 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

Setup Sansan with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Vercel AI SDK streams live contact data

The `search_biz_cards` tool queries your Sansan database the moment a user types a name. Your AI client streams the matching profiles directly into the DOM before the full response finishes. End users see contact details appear instantly instead of staring at a loading spinner. You wire `get_biz_card` and `get_person` to fetch specific records when someone clicks a profile card in your Next.js app. The MCP Server handles the remote execution while Vercel manages the chunked transfer. That means zero latency anxiety for your sales team.

Map organizational structures on the edge

The `list_departments` tool pulls the entire corporate hierarchy into your Vercel edge functions. You pass this context to your language model to automatically route internal requests or build dynamic org charts. The model knows exactly who reports to whom without you writing custom sync logic. Calling `list_users` alongside `list_persons` lets your frontend cross-reference internal employees with external scanned contacts. If a user needs to know who at your company met a specific client, the agent correlates the records. It happens fast enough to render before the page transition completes.

Filter networks by custom tags

The `list_tags` tool fetches every custom label your team applied to physical business cards during networking events. You feed these tags into a dropdown component, letting users filter thousands of records instantly. When they select a tag, the agent triggers `list_biz_cards` to pull the exact batch. This setup skips the traditional REST API boilerplate. You provide the tools to the Vercel AI SDK, and the language model decides when to fetch the filtered lists based on the user's prompt. You just handle the UI state while the framework handles the data ingestion.

Setup guide

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

Install the @ai-sdk/mcp package. Call createMCPClient with your HTTP transport URL, then pass mcpClient.tools() into your streamText function. Always call mcpClient.close() when the stream finishes.

The SDK itself streams the live response from the MCP connection. You handle caching at the Next.js route level or edge function. This prevents redundant calls to search_biz_cards for common queries.

Yes. The HTTP transport protocol used by the MCP standard is fully compatible with edge runtimes. You avoid heavy cold starts when querying organizational data.

Use list_biz_cards with strict pagination limits in your prompt instructions. The language model will fetch manageable chunks, keeping the React render cycle smooth.

The server processes raw contact names, phone numbers, and department hierarchies. Vinkius operates a zero-trust V8 Isolate Sandbox that destroys the runtime immediately after execution. No personal identifiers persist on our infrastructure.

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