How to Use the Axiom MCP in Vercel AI SDK

Q: How do I run an Axiom query inside Vercel AI SDK?

Call mcpClient.tools() to grab the runquery tool, then pass it directly to streamText. Your Next.js frontend will immediately receive raw log events as the APL query executes.

Q: What is the best way to clean up Axiom resources?

Always invoke mcpClient.close() once your streaming session finishes. This prevents connection leaks in your Next.js serverless functions while using MCP tools like deletedataset.

Pipe live Axiom log queries and dataset metrics directly into your Next.js UI 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 Axiom MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream Axiom query results directly to React

The `run_query` tool lets your Vercel AI SDK application fetch live log data and render the raw events on screen as they arrive. Instead of waiting for a backend API to bundle a massive payload, the client streams the APL query execution directly to the user's viewport. You build responsive operational interfaces where developers see their live application logs appear dynamically. Using `list_datasets` alongside streaming UI components gives your users immediate, interactive access to their telemetry without page refreshes.

Build interactive dataset managers

The `create_dataset` tool enables your Next.js application to spin up new storage buckets on demand during user onboarding. Because the Vercel AI SDK integrates tools natively into your UI flow, your users can watch the system configure their log pipelines in real-time. You don't need complex loading states when managing telemetry resources. Passing `list_datasets` and `update_dataset` directly to the streaming client lets the interface update its status indicators instantly as the backend confirms the setup.

Live monitor configuration via MCP Server

The `create_monitor` tool hooks directly into your application's setup assistant to configure alerting rules on the fly. Users describe what they want to watch, and your Vercel AI SDK client instantly maps that to an active Axiom monitor. By piping `list_notifiers` and `create_notifier` to the edge-compatible client, you construct a complete alerting setup wizard. Your users see their notification channels spin up live without waiting for standard API roundtrips.

Setup guide

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

Call `mcpClient.tools()` to grab the `run_query` tool, then pass it directly to `streamText`. Your Next.js frontend will immediately receive raw log events as the APL query executes.

Yes, this server runs in a secure V8 sandbox, making it fully compatible with edge runtimes. You just initialize the HTTP transport using `createMCPClient` inside your Next.js route handler.

Vinkius handles the underlying API tokens securely so you do not expose keys to the client. You provide a single endpoint token to `createMCPClient`, and the managed gateway handles the rest.

Always invoke `mcpClient.close()` once your streaming session finishes. This prevents connection leaks in your Next.js serverless functions while using MCP tools like `delete_dataset`.

All ingested log payloads and APL query results remain encrypted within Vinkius's ephemeral V8 MCP sandbox. Your sensitive telemetry never persists on our servers, and the gateway acts as a pass-through directly to your secure datasets.

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