How to Use the Moxie MCP in Vercel AI SDK

Q: How do I use the Vercel AI SDK to search for Moxie invoices?

You'll call mcpClient.tools() to get the searchinvoices tool. Pass that tool to the generateText or streamText function along with your prompt, like "find all unpaid invoices for 'Client Corp'." The AI SDK handles calling the tool and returning the data.

Q: Can I create new clients in Moxie from my Next.js app?

Yes. The createclient tool is exposed through the Moxie MCP Server. Your agent can use it to create a new client record based on user input from your frontend.

Q: What's the best way to list all my Moxie projects with the Vercel AI SDK?

Use the searchprojects tool. While you can use listclients first, searchprojects is more direct if you just need project data. You can filter by status to find only active projects, for instance.

Connect Moxie to your frontend and stream business data directly into your UI with the Vercel AI SDK. No more 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 Moxie MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build Live Client Dashboards

Give your clients a real-time view of their account. Your agent can use `list_clients` and `search_projects` to find their work, then stream the results directly into a Next.js or Svelte component. The user sees project statuses and tasks appearing live on the page. This isn't just for reading data. You can build interactive forms where an agent executes actions in the background. For example, a user fills out a form, and your agent uses `create_ticket` to submit a support request. The UI updates instantly with the new ticket ID, confirming the action without a page refresh.

Interactive Invoicing and Time Logging

Turn tedious financial tasks into a simple conversation. An agent can guide a user through creating an invoice, using `search_projects` to find billable hours and `create_invoice` to generate the document. The Vercel AI SDK streams the draft invoice into the UI as it's built. Time tracking gets a lot faster, too. A developer can build a simple input where a user just types "logged 2 hours on Project X design phase." The agent parses it and calls `create_time_entry` via this MCP Server. The user gets immediate confirmation right in the chat.

Conversational Project Setup with your MCP Server

Onboard new clients without ever opening the Moxie app. You can build a chatbot that asks for the client's name, project scope, and initial tasks. As the user provides information, your agent makes calls to `create_client`, `create_project`, and `create_task` in sequence. The user sees their new project getting built step-by-step. This is perfect for internal tools that let your sales team set up new accounts for the delivery team. It reduces errors and makes sure nothing gets missed.

Setup guide

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

You'll call `mcpClient.tools()` to get the `search_invoices` tool. Pass that tool to the `generateText` or `streamText` function along with your prompt, like "find all unpaid invoices for 'Client Corp'." The AI SDK handles calling the tool and returning the data.

Yes. The `create_client` tool is exposed through the Moxie MCP Server. Your agent can use it to create a new client record based on user input from your frontend.

Use the `search_projects` tool. While you can use `list_clients` first, `search_projects` is more direct if you just need project data. You can filter by status to find only active projects, for instance.

Absolutely. The Vercel AI SDK is designed for streaming. When your agent uses a tool like `list_users`, the results can be streamed into your UI, populating a list of users in real time.

This server only interacts with your Moxie account data: clients, contacts, projects, tasks, invoices, time entries, and expenses. Your Vinkius server is ephemeral and runs in a zero-trust sandbox, so the data is only processed for the immediate request and never stored.

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