How to Use the Addepar MCP in Vercel AI SDK

Connect Addepar data directly to your React frontend using the Vercel AI SDK. Stream portfolio analytics without loading spinners.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Addepar MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream Addepar data into your Vercel AI SDK app

You pull client accounts immediately using `list_entities` and check their specific data with `get_entity_details`. Vercel AI SDK streams this text straight to your Next.js components while the fetch happens in the background. End users watch their wealth summaries appear word by word instead of staring at a blank screen. Then you hit `get_portfolio_analytics` to grab performance metrics. Your React frontend renders the yield charts dynamically as the chunks arrive over the wire. Nobody waits for massive API payloads to resolve before seeing their money.

Render live asset holdings

Fetching current positions relies on `get_position_details` to pull the exact securities inside a portfolio. This MCP Server handles the Addepar authentication layer while your Edge Function pipes the asset list straight to the browser. Users ask your chat interface about their Apple stock exposure. The agent calls the tool, formats the JSON into a readable markdown table, and the UI updates instantly. It feels instantaneous.

Surface financial activity instantly

Tracing money movement requires calling `list_transactions` to get historical deposits, withdrawals, and trades. The agent parses the raw ledger entries and groups them by month. Building this manually takes weeks of wrangling pagination logic. Using this MCP integration, you just pass the tool array to the stream and let the language model summarize the cash flow.

Setup guide

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

Run npm install ai @ai-sdk/mcp in your terminal. Initialize the connection using createMCPClient with your HTTP transport endpoint. Call mcpClient.tools() and pass the array directly to your streamText function.

Yes, if your React components support tool-calling rendering. The agent fetches data from the API and yields a UI component while the text streams.

You skip writing the glue code. The MCP protocol standardizes the tool definitions so the language model knows exactly how to query accounts without you writing custom fetching logic.

The HTTP transport works perfectly in Edge runtimes. Just remember to call mcpClient.close() when your route handler finishes executing.

Vinkius isolates your server in a V8 sandbox. When your agent reads ledger entries or holding amounts, the ephemeral container processes the request and immediately dies, ensuring no client wealth records ever touch a persistent disk.

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