How to Use the Honeycomb MCP in Vercel AI SDK

Q: How do I handle Honeycomb rate limits inside a Vercel AI SDK edge function?

You should configure your streamText call with a retry limit when calling runquery. Because edge functions have short timeouts, you can offload the polling of getqueryresult to a background worker to avoid blocking the main UI thread.

Q: Can I use Vercel AI SDK to build interactive Honeycomb query builders?

Yes, you can feed the output of listdatasetcolumns directly into the SDK's tool call parameters. This allows your LLM to generate valid createqueryspecification payloads that match your active telemetry schema.

Get real-time Honeycomb query execution and deployment markers streaming directly into your Next.js UI with 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 Honeycomb MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream Honeycomb Queries to Next.js via MCP Server

This MCP Server exposes `run_query` so your AI client can execute telemetry checks directly from a Vercel Edge Function. Instead of waiting for a slow backend response, the Vercel AI SDK streams the query execution ID straight to your React frontend. Once the client receives the ID, it polls for the payload using `get_query_result`. Your users watch the telemetry tables populate row-by-row in real-time instead of staring at a static loading spinner.

Interactive Dataset Inspection

The `list_dataset_columns` tool lets your Vercel AI SDK application inspect your telemetry schema on the fly. This means your UI can dynamically build auto-complete dropdowns for your SRE team as they type queries. To fetch the correct schema, the agent calls `list_datasets` to resolve the team's active dataset slugs first. Your Next.js interface then renders the columns instantly using React Server Components.

Direct Deployment Annotations

The `create_marker` tool allows your Next.js deployment pipeline to flag production changes on your Honeycomb timeline using this MCP Server. When a Vercel deployment completes, the SDK triggers the marker creation with the exact commit message. SREs view these markers alongside query results by running `list_markers` in their chat interface. This keeps your deployment events perfectly aligned with your telemetry data in a single UI view.

Setup guide

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

You should configure your `streamText` call with a retry limit when calling `run_query`. Because edge functions have short timeouts, you can offload the polling of `get_query_result` to a background worker to avoid blocking the main UI thread.

Yes, you can feed the output of `list_dataset_columns` directly into the SDK's tool call parameters. This allows your LLM to generate valid `create_query_specification` payloads that match your active telemetry schema.

You define the credentials in your Vercel environment variables and pass them when creating the HTTP transport. The SDK routes these to the MCP endpoint, ensuring your telemetry keys never expose themselves to the frontend.

The SDK handles large JSON payloads by chunking the text stream. You can write a custom UI component in React that parses the partial JSON as it arrives, keeping the browser responsive.

The MCP Server runs inside a zero-trust V8 sandbox, meaning your dataset columns and query specifications are never cached or stored. Your telemetry metadata travels directly between Vercel's edge network and Honeycomb's secure API.

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