How to Use the GlobalGiving MCP in Vercel AI SDK

Q: How do I stream GlobalGiving data using the Vercel AI SDK?

Use createMCPClient to connect to the server's HTTP endpoint. Pass the tools returned by mcpClient.tools() directly into streamText to let your agent call listprojectsbytheme and stream results live.

Show live GlobalGiving project metrics and charity metadata directly in your Next.js UI 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 GlobalGiving MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream GlobalGiving metrics directly to your Vercel AI SDK UI

`list_projects_by_theme` pulls active crowdfunding campaigns and sends them straight to your React component without waiting for a full page reload. Your AI client fetches the latest funding numbers and streams the JSON chunks so users see the numbers tick up in real-time. You'll build this by passing the MCP server tools to `streamText`. The Vercel AI SDK handles the edge-runtime connection, executing the request and rendering the charity data instantly as it arrives from the GlobalGiving API.

Query specific humanitarian sectors on the edge

`find_education_initiatives` and `find_health_initiatives` isolate specific sectors so your agent doesn't waste tokens on irrelevant data. The edge-compatible client runs these targeted lookups in under 100 milliseconds, bypassing heavy database roundtrips. By declaring these specific endpoints in your tool definitions, you let your agent fetch only what the user asked for. That's no bloated payloads—just direct sector metrics served to your frontend.

Inspect organization metadata inside your chat interface

`get_charity_details` extracts the operational history and tax status of any registered nonprofit in the system. Your agent calls this tool to verify legitimacy before presenting donation options to your users. This MCP Server runs inside a secure V8 isolate, meaning your user-facing app stays lightweight while executing these deep metadata lookups. You get clean, verified organization profiles without manual parsing.

Setup guide

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

Use `createMCPClient` to connect to the server's HTTP endpoint. Pass the tools returned by `mcpClient.tools()` directly into `streamText` to let your agent call `list_projects_by_theme` and stream results live.

Yes, the server runs in an ephemeral sandbox that connects over standard HTTP transport. The Vercel AI SDK handles this on the edge, running tools via the MCP Server without cold-start delays.

Vinkius manages the API keys and returns a single endpoint token. You pass this token in your client setup, allowing your agent to run `search_nonprofit_projects` through the MCP Server without hardcoding credentials in your frontend code.

The SDK catches the tool execution error and passes it to your UI stream. You can display a fallback state while your agent tries a broader query like `list_all_projects` to keep the user experience smooth.

The server only processes nonprofit metadata, country codes, and project descriptions. Since everything runs in an isolated sandbox, your search queries are never stored or shared.

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