How to Use the GivingFuel MCP in Vercel AI SDK

Q: How do I authenticate the GivingFuel MCP Server inside a Vercel AI SDK project?

You use createMCPClient with an HTTP transport pointing to your Vinkius endpoint. Pass your single Vinkius token in the headers, and Vinkius handles the underlying GivingFuel API authentication securely. Always call mcpClient.close() when the session ends.

Q: Can I stream GivingFuel transactions to a React frontend without loading spinners using Vercel AI SDK?

Yes, by passing listrecentdonations to the streamText function. The Vercel AI SDK streams the raw JSON chunks of the latest 10 orders directly to your UI components as they arrive.

Q: What is the best way to filter GivingFuel orders by status using Vercel AI SDK?

Pass the filterordersbystatus tool to your agent's tool array. The AI client will automatically invoke it when a user asks to see completed or failed orders, registering the tool call seamlessly through the MCP Server.

Stream real-time GivingFuel transaction data directly into your React components using the 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 GivingFuel MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream live transaction counts to your Vercel AI SDK UI

The `list_recent_donations` tool lets your agent pull the latest 10 orders straight from GivingFuel without database latency. By coupling this with the Vercel AI SDK, you stream these transactions directly to a live-updating dashboard component. The end user watches the donation feed update in real-time as the agent processes the stream. To verify settled funds without slowing down the frontend, the agent runs `list_financial_transactions` in the background. This ensures you display completed credit card charges rather than pending attempts. Bottom line: your users get instant visual feedback while your underlying React components maintain accounting accuracy.

Lookup donor profiles inline inside your Next.js chat

The `list_crm_contacts` tool exposes complete donor history to the Vercel AI SDK runtime on the Edge. When a customer support agent types a name, the AI client invokes this tool alongside `list_donation_registrants` to resolve the contact record instantly. No spinners are needed because the raw text streams directly into the chat bubble. You implement this by feeding the output of `mcpClient.tools()` directly into `streamText`. The system matches the incoming search term to GivingFuel records, meaning your support team checks registration status without leaving the communication thread. Let's run it on Edge Functions to minimize cold starts.

Audit campaign pages via Vercel AI SDK tool calls

The `list_fundraising_pages` tool allows your agent to fetch active donation pages and their configuration details. Using the Vercel AI SDK, your application can compare these pages against peer-to-peer initiatives retrieved via `list_peer_campaigns`. This setup lets you build automated audit reports that render live inside your React admin panel. This MCP Server integration runs inside Vinkius's secure sandbox, protecting your API keys from client-side exposure. By calling `mcpClient.close()` at the end of the Edge Function execution, you prevent resource leaks while maintaining a direct, secure pipeline to GivingFuel's financial endpoints.

Setup guide

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

You use `createMCPClient` with an HTTP transport pointing to your Vinkius endpoint. Pass your single Vinkius token in the headers, and Vinkius handles the underlying GivingFuel API authentication securely. Always call `mcpClient.close()` when the session ends.

Yes, by passing `list_recent_donations` to the `streamText` function. The Vercel AI SDK streams the raw JSON chunks of the latest 10 orders directly to your UI components as they arrive.

You should implement a caching layer or use Edge-level rate limiting before the agent invokes `list_financial_transactions`. Vinkius executes the MCP Server tools within ephemeral V8 isolates to keep latency under two seconds, but you must manage rapid consecutive calls.

Pass the `filter_orders_by_status` tool to your agent's tool array. The AI client will automatically invoke it when a user asks to see completed or failed orders, registering the tool call seamlessly through the MCP Server.

Vinkius runs the server in a zero-trust, ephemeral sandbox where donor profiles from `list_crm_contacts` are never cached. The Vercel AI SDK communicates with the server over an encrypted HTTP transport, keeping financial transactions isolated from public exposure.

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