How to Use the Donately MCP in Vercel AI SDK

Q: How do I initialize the Donately MCP Server in Vercel AI SDK?

Install @ai-sdk/mcp and use createMCPClient pointing to the Vinkius HTTP endpoint. Pass the tools directly into generateText or streamText to let your agent call fundraising actions. Always call mcpClient.close() when the execution context ends.

Q: Can I use the Donately MCP Server within a Vercel AI SDK Edge Function?

Yes, the createdonation tool is fully compatible with edge runtimes because the MCP transport runs over lightweight HTTP. Your agent can process a donation payload and trigger the creation immediately during a live chat session.

Q: How does Vercel AI SDK handle pagination for Donately records?

The listpeople tool accepts pagination parameters that your TypeScript code can pass dynamically. The agent analyzes the returned donor list and can request the next page if the user asks for more records.

Q: What is the best way to handle tool approvals for Donately mutations?

You can intercept the tool call before executing createdonation to ask for user confirmation. This ensures no unauthorized transactions occur while your agent manages fundraising data.

Pipe real-time fundraising data directly into your Next.js frontend using the Vercel AI SDK and this MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Donately MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream live donor feeds with Vercel AI SDK

The `list_donations` tool lets your AI client fetch the latest incoming contributions and push them directly to a live-updating React component. Instead of waiting for a slow backend polling system, your application streams actual donor names and amounts straight to the browser. By passing the MCP tool outputs directly to `streamText`, you bypass traditional API routing middleware. The frontend renders active donation records instantly as the server processes them, keeping your fundraising dashboard updated with zero lag.

Query campaign status in Next.js Edge Functions

The `get_campaign` tool queries the exact progress of any active fundraising campaign to display real-time progress bars. This setup runs on edge nodes, meaning your donors get instant feedback on campaign goals without hitting cold-start delays. Using `list_campaigns` alongside this endpoint allows your interface to map out multiple active fundraising initiatives. Your application pulls the raw numbers directly from your Donately dashboard, rendering progress updates on the fly.

Fetch active subscriptions directly inside the chat UI

The `get_subscription` tool retrieves active recurring plans so your donors can review their giving schedules inside a conversational UI. Your Vercel AI SDK agent reads this data and formats it into clean, interactive UI elements without requiring hardcoded API wrappers. By combining this with `list_subscriptions`, you let users filter their active giving plans by date or amount. The agent pulls the exact subscription details from Donately, presenting them in the chat window in under a second.

Setup guide

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

Install `@ai-sdk/mcp` and use `createMCPClient` pointing to the Vinkius HTTP endpoint. Pass the tools directly into `generateText` or `streamText` to let your agent call fundraising actions. Always call `mcpClient.close()` when the execution context ends.

Yes, the `create_donation` tool is fully compatible with edge runtimes because the MCP transport runs over lightweight HTTP. Your agent can process a donation payload and trigger the creation immediately during a live chat session.

The `list_people` tool accepts pagination parameters that your TypeScript code can pass dynamically. The agent analyzes the returned donor list and can request the next page if the user asks for more records.

You can intercept the tool call before executing `create_donation` to ask for user confirmation. This ensures no unauthorized transactions occur while your agent manages fundraising data.

Your donor contact details and payment records are protected by Vinkius's zero-trust sandboxed MCP environment. The SDK never stores sensitive data like email addresses or subscription IDs, routing them through transient memory only.

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