How to Use the Salsa Engage MCP in Vercel AI SDK

Q: Can I use Vercel AI SDK to filter Salsa Engage groups?

Yes. Your agent calls listsupportergroups to grab your existing lists, then uses that context to organize contacts. The SDK streams the categorized results directly into your UI, so your team sees group assignments update in real-time.

Build real-time non-profit dashboards where your Vercel AI SDK client streams live supporter updates straight to your UI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Salsa Engage MCP to Vercel AI SDK

Create your Vinkius account to connect Salsa Engage to Vercel AI SDK — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Salsa Engage with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Real-time supporter updates for Vercel AI SDK

The `upsert_supporter_profile` tool lets your app modify or create donor profiles on the fly. When a user edits a contact in your Next.js frontend, this MCP Server processes the change and streams the updated record back immediately. You avoid the lag of traditional API polling by letting your edge functions write directly to Salsa Engage. Your Vercel AI SDK setup feeds these updates into a live state machine. By pairing this with `assign_supporters_to_group`, your interface highlights group membership changes the millisecond they happen. Users see immediate visual confirmation instead of staring at a loading spinner.

Live fundraising dashboards with Vercel AI SDK

The `get_engagement_metrics` tool pulls raw performance numbers directly into your streaming UI components. Your agent feeds these metrics into charts that render progressively as the data arrives. This setup prevents page freezes when fetching heavy datasets, making your internal reports load instantly. To give your team a complete financial picture, the server pulls in offline data via `list_offline_donations`. Edge functions process these offline records, rendering progress bars that update item by item. Your team gets a live look at fundraising targets without manual browser refreshes.

Instantly segment audiences in your Next.js app

The `list_supporter_segments` tool exposes your defined donor segments directly to your AI client's context. Client-side code uses these segments to build dynamic filtering interfaces that react as the user types. This eliminates the need to build complex database queries from scratch. When you need to adjust these segments, the `upsert_supporter_group` tool updates your Salsa Engage setup right from the chat box using this MCP Server. Your agent handles the payload formatting and executes the write, updating your UI state in one pass. It cuts out the middleman, keeping your donor lists clean.

Setup guide

Set up Salsa Engage 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 Salsa Engage 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 Salsa Engage 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 Salsa Engage. 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 Salsa Engage 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 Salsa Engage MCP in Vercel AI SDK

You initialize the MCP client in your route handler and pass the tools directly to `streamText`. The `list_supporters` tool runs on the edge, sending supporter data straight to your React components. Don't forget to call `mcpClient.close()` once the stream finishes.

Yes. Your agent calls `list_supporter_groups` to grab your existing lists, then uses that context to organize contacts. The SDK streams the categorized results directly into your UI, so your team sees group assignments update in real-time.

Absolutely. The server connects via HTTP or SSE, keeping your edge runtimes lightweight. It runs tools like `list_engagement_activities` without heavy node dependencies, which keeps your lambda cold starts under 50 milliseconds.

The SDK processes responses as they arrive, but you should monitor your API health. The `check_api_health` tool lets your agent verify connectivity before starting heavy operations. If the endpoint is down, your UI can catch the error early and warn the user.

Your supporter profiles and donation records stay inside a sandboxed V8 isolate. Vinkius secures your credentials with a single endpoint token, meaning your Vercel AI SDK code never exposes raw API keys to the client browser.

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