How to Use the GaggleAMP MCP in Vercel AI SDK

Q: How do I connect GaggleAMP to Vercel AI SDK?

You install @ai-sdk/mcp and initialize the client using createMCPClient with your Vinkius HTTP endpoint. This MCP integration exposes tools like listactivities directly to your streaming agent.

Q: Can I stream real-time advocate rankings using GaggleAMP and Vercel AI SDK?

Yes. Your agent calls gettopadvocates through the SDK to stream the highest-performing employee names and scores directly into your Next.js UI.

Q: How does Vercel AI SDK handle reward redemptions on GaggleAMP?

The agent uses redeemrewarditem to process a claim when a user selects an item from the list. The SDK streams the confirmation status back to the frontend immediately.

Q: How do I manage multiple advocate groups?

Use listallgaggles to find the specific group you want to target. The MCP Server returns all groups associated with your account so your agent can query members or assign activities.

Build live-updating employee advocacy dashboards where Vercel AI SDK streams real-time social activity stats directly to your team.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect GaggleAMP MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream live advocacy metrics with Vercel AI SDK

The `get_activity_engagement` tool feeds raw social performance data directly into your edge-rendered UI components. Your AI client grabs post interactions and streams them to the screen, so managers see actual numbers load block-by-block instead of staring at a blank screen. You configure the client using `createMCPClient` to pipe these live stats straight into React or Next.js frontends through an MCP connection. When a user checks on their active campaigns, the SDK fetches the numbers and renders the engagement metrics instantly without requiring manual page refreshes.

Distribute social tasks instantly from the UI

The `create_activity` tool lets your agent publish new sharing tasks directly to your company's Gaggle feed from your custom dashboard using the MCP Server. You don't have to open a separate portal to push a new post prompt to your team. By integrating this toolset with `streamText`, your custom interface allows managers to draft a post, have the agent refine it, and publish the task immediately. The tool handles the API communication in the background while the UI shows the status in real time.

Track and display advocate points live

The `get_member_points` tool retrieves the exact point totals for any employee registered in your advocacy program. This lets your frontend display real-time leaderboards by pulling data directly from the API. Your agent uses `list_gaggle_members` alongside the points tool to build dynamic scoreboard components that update as soon as someone shares a post. The Vercel AI SDK handles the data stream, keeping the team leaderboard accurate and competitive.

Setup guide

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

You install `@ai-sdk/mcp` and initialize the client using `createMCPClient` with your Vinkius HTTP endpoint. This MCP integration exposes tools like `list_activities` directly to your streaming agent.

Yes. Your agent calls `get_top_advocates` through the SDK to stream the highest-performing employee names and scores directly into your Next.js UI.

The agent uses `redeem_reward_item` to process a claim when a user selects an item from the list. The SDK streams the confirmation status back to the frontend immediately.

Use `list_all_gaggles` to find the specific group you want to target. The MCP Server returns all groups associated with your account so your agent can query members or assign activities.

Vinkius processes all requests in an ephemeral V8 sandbox, meaning your advocate points from `get_member_points` are never stored on our servers. The connection to your GaggleAMP account uses a single secure token that is encrypted in transit and discarded immediately after the tool execution completes.

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