How to Use the Harvest MCP in Vercel AI SDK

Q: How do I handle Vercel AI SDK authentication with the Harvest MCP Server?

You pass your Vinkius endpoint token directly into the createMCPClient transport configuration. The SDK manages authorization headers automatically, so your Next.js edge functions never expose your raw API keys to the browser.

Q: Can I stream Harvest project metrics in Vercel AI SDK with this MCP?

Yes. You call the listprojects tool inside streamText to render active project files in real-time. This lets your React components display live project hours without requiring manual page refreshes.

Q: What is the best way to clean up connections between Harvest and Vercel AI SDK?

Always execute the mcpClient.close() method when your serverless execution finishes. This prevents open socket leaks in your Vercel edge environment and keeps your serverless runtimes fast.

Q: How can my React interface display client lists using these tools?

Execute listclients and pass the raw JSON payload straight to your UI components. The SDK handles the data transfer, allowing your agent to update the customer directory dynamically.

Build Next.js apps that stream live Harvest invoice drafts and active project time entries directly into your UI 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 Harvest MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Live-streaming invoice creation in Vercel AI SDK

The `create_invoice` tool lets your Vercel AI SDK application generate client bills on the fly via this MCP Server. Instead of making users wait for a backend cycle to finish, the tool outputs draft invoices directly to the frontend context. This immediate feedback prevents interface lag during heavy billing cycles. Your application passes the tools array to `streamText` to trigger the invoice creation process. When the client confirms, the SDK renders the invoice details in a native React component. You get immediate UI updates without polling a database.

Instant client lookup inside Next.js components

The `list_clients` tool pulls your complete client roster directly into your Vercel AI SDK edge functions using our managed MCP setup. You avoid long loading spinners by feeding client IDs straight to the interface as the agent fetches them. This real-time data injection keeps your frontend responsive. Your agent calls `get_client` to populate client metadata card components. By using edge-compatible modules, the client profile loads instantly in the browser. Users see client records update as they speak to the chat interface.

Real-time time logging and tracking displays

The `list_time_entries` tool exposes billable hours directly to your AI-driven dashboard. Your user sees their logged hours populate a chart while the agent calculates the totals. This direct data stream bypasses slow intermediate API servers. Developers bind these tool outputs directly to interactive UI state. You call `list_projects` to let the user select a project, then display the tracked hours immediately. It makes time auditing feel instant.

Setup guide

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

You pass your Vinkius endpoint token directly into the `createMCPClient` transport configuration. The SDK manages authorization headers automatically, so your Next.js edge functions never expose your raw API keys to the browser.

Yes. You call the `list_projects` tool inside `streamText` to render active project files in real-time. This lets your React components display live project hours without requiring manual page refreshes.

Always execute the `mcpClient.close()` method when your serverless execution finishes. This prevents open socket leaks in your Vercel edge environment and keeps your serverless runtimes fast.

Execute `list_clients` and pass the raw JSON payload straight to your UI components. The SDK handles the data transfer, allowing your agent to update the customer directory dynamically.

Your client details and invoice financial records travel directly through an ephemeral, zero-trust V8 sandbox. No database stores your financial logs, meaning your client names and hourly rates remain secure and private.

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