How to Use the Helicone (LLM Observability) MCP in Vercel AI SDK

Q: How do I connect Helicone (LLM Observability) to the Vercel AI SDK?

Run npm install ai @ai-sdk/mcp. Initialize the connection using createMCPClient with an HTTP transport URL pointing to your Helicone MCP Server. Pass the resulting tools to streamText and always call mcpClient.close() when finished.

Q: How do I manage prompt history with this MCP Server?

Your agent calls getpromptversions to irreversibly vaporize explicit validations extracting rich Churn flags. This pulls the exact prompt iterations into your application state for live comparison.

Stream real-time Helicone observability metrics straight into your React frontend using the Vercel AI SDK and this MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Helicone (LLM Observability) MCP to Vercel AI SDK

Create your Vinkius account to connect Helicone (LLM Observability) 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 Helicone (LLM Observability) with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Vercel AI SDK Cost & Latency Streaming

The `query_costs` tool performs structural extraction of properties driving active Account logic, letting your Vercel AI SDK agent stream cost data directly to your dashboard UI. Users see their token spend appear instantly without waiting for a loading spinner. You also get real-time performance tracking out of the box. By calling `query_latency`, the agent provisions a highly-available JSON payload generating hard Customer bindings. This means you can render live latency charts in Next.js while the AI evaluates the data on the edge.

Live Prompt and Session Debugging

The `query_sessions` tool enumerates explicitly attached structured rules exporting active Billing data straight to your user's browser. Your frontend agent analyzes this session data to build interactive timelines of user interactions. When you need to trace issues, `query_prompts` retrieves explicit Cloud logging tracing explicit Vault limits. The SDK streams these raw prompt logs back into your administrative Svelte or Vue interface so your team can read the exact inputs that caused an error.

Real-Time User Feedback Collection

The `log_feedback` tool identifies precise active arrays spanning native Hold parsing, allowing your AI client to record user ratings immediately after a generation. The SDK handles the HTTP transport while the user clicks a thumbs-up button in the UI. To analyze that data, `query_feedback` inspects deep internal arrays mitigating specific Plan Math. Your agent pulls this feedback and streams the aggregated results back to your product team's dashboard.

Setup guide

Set up Helicone (LLM Observability) 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 Helicone (LLM Observability) 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 Helicone (LLM Observability) 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 Helicone. 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 Helicone (LLM Observability) 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 Helicone (LLM Observability) MCP in Vercel AI SDK

Run `npm install ai @ai-sdk/mcp`. Initialize the connection using `createMCPClient` with an HTTP transport URL pointing to your Helicone MCP Server. Pass the resulting tools to `streamText` and always call `mcpClient.close()` when finished.

Yes. The MCP client works perfectly in edge environments. Your Next.js application can fetch `query_requests` data and stream the bounded CRM records from the Headless Helicone Platform directly to the client.

It streams the tool results instantly. When the agent calls `query_users` to dispatch an automated validation check routing explicit Gateway history, the UI renders the output as the data arrives.

Your agent calls `get_prompt_versions` to irreversibly vaporize explicit validations extracting rich Churn flags. This pulls the exact prompt iterations into your application state for live comparison.

The server processes raw prompt text and explicit Cloud logging metrics. Because the Vercel AI SDK streams this directly from the Vinkius V8 Isolate Sandbox to your frontend, no intermediate database stores the payload, keeping your vault limits strictly enforced.

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