How to Use the Keywords AI MCP in Vercel AI SDK

Q: How do I connect Keywords AI with Vercel AI SDK?

Install @ai-sdk/mcp. Use createMCPClient with your endpoint URL, then call mcpClient.tools() and pass the array directly into your streamText function.

Q: Can the Vercel AI SDK stream Keywords AI request logs to the browser?

Yes. When your agent calls listrequests, the tool execution streams directly to your React or Next.js frontend. The user sees the logs appear instantly.

Q: How does Keywords AI handle Vercel AI SDK authentication?

You pass an authProvider configuration when initializing the MCP client. This handles the OAuth handshake required to access your gateway data.

Stream live LLM API costs and request analytics directly into your React interfaces using the 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 Keywords AI MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream LLM Usage Data with Vercel AI SDK

The Keywords AI MCP server exposes `get_analytics` and `get_usage_stats` so your agent can pull real-time token metrics across all providers. You pass these tools into `generateText`, and the client fetches the exact cost data needed to render live billing dashboards for your end users. Stop making users wait for a spinning loader while you aggregate metrics. Because Vercel AI streams tool calls directly to the frontend, you can run `list_requests_by_model` and watch the request logs populate in your Svelte or Next.js app the second the database returns them.

Catch API Failures in Real Time

`check_keywordsai_status` and `list_alerts` give your application instant visibility into provider health and rate limits. If a primary provider starts throwing 500 errors, your client detects the alert and immediately shifts traffic to a fallback model. You don't need a separate background cron job to track uptime. The agent pulls the active alert queue during the active session. If an alert triggers, your UI updates instantly to warn the user about degraded performance.

Manage Team Quotas On the Fly

Using `list_users` and `get_user`, your agent inspects exactly who is burning through your API budget. Pair this with `get_credits` to check the remaining balance before executing expensive multi-step prompts. The integration handles the heavy lifting of user management without leaving the chat interface. You ask your AI client for a breakdown of the engineering team's spend, and it streams a formatted table of current usage limits straight to the browser.

Setup guide

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

Install `@ai-sdk/mcp`. Use `createMCPClient` with your endpoint URL, then call `mcpClient.tools()` and pass the array directly into your `streamText` function.

Yes. When your agent calls `list_requests`, the tool execution streams directly to your React or Next.js frontend. The user sees the logs appear instantly.

You pass an `authProvider` configuration when initializing the MCP client. This handles the OAuth handshake required to access your gateway data.

The tool returns an error state. You write error handling logic in your UI components to display a fallback message instead of breaking the entire stream.

This server processes API request logs, token usage metrics, and user identifiers. Vinkius runs the server in an ephemeral V8 Isolate sandbox that destroys itself after the connection closes, ensuring your usage data never persists on our infrastructure.

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