How to Use the Keen MCP in Vercel AI SDK

Q: How do I register Keen tools in my Vercel AI SDK app?

Install @ai-sdk/mcp and create a client pointing to your Vinkius endpoint. You then pass mcpClient.tools() into generateText or streamText to let your agent call tools like recordevent or countunique. Don't forget to call mcpClient.close() when your edge function finishes.

Q: Can my agent run Keen saved queries?

Yes. The listsavedqueries tool exposes your pre-configured Keen queries directly to your agent. This is much faster than having the agent build a complex sumproperty query from scratch.

Q: Is my event data secure when using this server?

Your raw JSON event payloads sent via recordevent go directly through a secure V8 sandbox on Vinkius. We do not store your Keen API keys or query results. Everything is processed in an ephemeral environment and sent straight to Keen.io.

Feed real-time event metrics directly to your users with the Keen MCP server for 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 Keen MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream raw event logs directly to frontend components

The `record_event` tool sends user actions to Keen.io while Vercel AI SDK renders the confirmation on screen without delay. Your UI doesn't freeze waiting for a database response. Instead of standard loading spinners, users see data stream instantly. You get clean frontend code without manual state management.

Query Keen database metrics using the Vercel AI SDK

This MCP server exposes `count_events` and `sum_property` directly to your client-side application. Your LLM agent processes these numbers behind the scenes to update your charts. You don't need to write custom API endpoints for every new metric. Just let the agent run calculations and pipe the numbers into your React state.

Discover event schemas dynamically

The `list_collections` and `get_project_details` tools let your AI client understand your Keen data structure. This means the agent can inspect what properties exist before writing a query. No more hardcoded schema maps in your codebase. Your Next.js app queries whatever event collections exist in real time.

Setup guide

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

Install `@ai-sdk/mcp` and create a client pointing to your Vinkius endpoint. You then pass `mcpClient.tools()` into `generateText` or `streamText` to let your agent call tools like `record_event` or `count_unique`. Don't forget to call `mcpClient.close()` when your edge function finishes.

Yes, this setup works perfectly in Edge environments. The MCP server processes tools like `sum_property` and `average_property` remotely, keeping your edge bundle light. You avoid pulling heavy database drivers into your serverless functions.

The Vercel AI SDK handles tool calls sequentially, so rapid-fire queries like `select_unique` won't overwhelm your limits under normal usage. If you expect high traffic, cache the output of tools like `list_saved_queries` to save API quota. This keeps your user-facing chat responses fast.

Yes. The `list_saved_queries` tool exposes your pre-configured Keen queries directly to your agent. This is much faster than having the agent build a complex `sum_property` query from scratch.

Your raw JSON event payloads sent via `record_event` go directly through a secure V8 sandbox on Vinkius. We do not store your Keen API keys or query results. Everything is processed in an ephemeral environment and sent straight to Keen.io.

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