4,500+ servers built on MCP Fusion
Vinkius
Amplitude logo
Vinkius
Vercel AI SDK logo

How to Use the Amplitude MCP in Vercel AI SDK

Stream live Amplitude product analytics straight into your React or Next.js frontends using the Vercel AI SDK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

Amplitude MCP on Cursor AI Code Editor MCP Client Amplitude MCP on Claude Desktop App MCP Integration Amplitude MCP on OpenAI Agents SDK MCP Compatible Amplitude MCP on Visual Studio Code MCP Extension Client Amplitude MCP on GitHub Copilot AI Agent MCP Integration Amplitude MCP on Google Gemini AI MCP Integration Amplitude MCP on Lovable AI Development MCP Client Amplitude MCP on Mistral AI Agents MCP Compatible Amplitude MCP on Amazon AWS Bedrock MCP Support
MCP Servers - Free for Subscribers
Vercel AI SDK

Connect Amplitude MCP to Vercel AI SDK

Create your Vinkius account to connect Amplitude 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

Build live funnels with Vercel AI SDK

The `get_funnel` tool pulls exact conversion drop-offs between your critical product milestones. Your AI client passes comma-separated event names and date ranges directly to the Amplitude MCP Server. Instead of making users wait for heavy BI dashboards to load, the Vercel AI SDK streams those conversion steps straight into your UI components. You wire this up by passing `mcpClient.tools()` into `streamText`. When an end user asks why signups dropped yesterday, the agent runs `event_segmentation` and streams back the exact feature usage stats. The data appears instantly on screen while the AI formulates its plain-English summary.

Stream raw user journeys

Calling `get_user_activity` grabs the precise click path of an individual account. This means your Next.js admin panel can let support reps ask the AI what a specific customer did before filing a ticket. The agent uses `search_users` to find the device ID, then pulls the activity stream. Because Vercel handles the transport layer efficiently, these raw event logs stream into your frontend chat interface without timeout errors. You get immediate visibility into edge cases. Just remember to call `mcpClient.close()` when the session ends to free up resources.

Render revenue and retention metrics

Running `revenue_analysis` alongside `get_retention` gives you the exact financial impact of user cohorts. The AI agent defines the acquisition event and the return event, then requests the daily breakdown. Your React frontend receives this structured data piece by piece. You can pipe these results directly into charting libraries. The user types a question about monthly active users, the agent fires `active_users`, and a live bar chart renders instantly. This setup turns static documentation sites into dynamic product analytics portals.

Setup guide

Set up Amplitude 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. 1

    Install dependencies

    Run npm install ai @modelcontextprotocol/sdk plus your preferred model provider (e.g. @ai-sdk/openai).

  2. 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. 3

    Discover and use tools

    Call mcpClient.tools() to auto-discover all Amplitude tools. Pass them directly to generateText() or streamText() — no manual schema definitions needed.

  4. 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 Amplitude transactions",
});

console.log(text);
await mcpClient.close();

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Amplitude. 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.

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 Amplitude MCP in Vercel AI SDK

Initialize the connection using `createMCPClient` with an HTTP transport URL pointing to Vinkius. Pass the resulting toolset into your `streamText` call. Your Next.js app will immediately recognize the analytics functions.
Yes, but you need to manage the stream. The `export_events` tool pulls raw data partitioned by hour. Vercel streams this back continuously, so pipe it into a background process rather than trying to render millions of rows in the browser.
Generating cohorts requires Amplitude to process millions of behavioral data points on their backend. The `get_cohort` tool polls the API until the download is ready. Your AI client will keep the connection open, so consider showing a progressive loading state in your UI.
You pass an `authProvider` configuration when calling `createMCPClient`. Vinkius manages the actual OAuth handshake. Your application only needs a single endpoint token to authorize the data requests.
The `search_users` tool transmits emails and device IDs directly to the Vinkius V8 Isolate Sandbox. This environment is ephemeral and zero-trust, meaning the memory wipes the instant the request finishes. No personal identifiers hit disk during the transaction.

Start using the Amplitude MCP today

We host it, we monitor it, we maintain it. You just paste one token.

Built & Managed by Vinkius 30s setup 10 tools

We've already built the connector for Amplitude. Just plug in your AI agents and start using Vinkius.

No hosting. No infrastructure. No complex setup.
All 10 tools are live and waiting. You're up and running in seconds.

Claude Claude
ChatGPT ChatGPT
Cursor Cursor
Gemini Gemini
Windsurf Windsurf
VS Code VS Code
JetBrains JetBrains
Vercel Vercel
+ other MCP clients

Vinkius gives your AI agents access to the full catalog of app connectors, all fully managed, secure, and enterprise-ready. One subscription, every tool you need.

Zero hosting required Full MCP catalog included Enterprise-grade security Auto-updated by Vinkius

Built, hosted, and secured by Vinkius. You just connect and go.