How to Use the AgentOps (Agent Telemetry and Monitoring) MCP in Vercel AI SDK

Q: How do I connect the AgentOps (Agent Telemetry and Monitoring) MCP Server to Vercel AI SDK?

Install @ai-sdk/mcp and use createMCPClient pointing to your Vinkius endpoint. Pass the tools array directly into generateText or streamText to let your agent fetch its own telemetry.

Q: Can I stream AgentOps (Agent Telemetry and Monitoring) trace data in real-time with Vercel AI SDK?

Yes, you pull trace data using gettrace and stream the raw metrics directly to your React components. This lets you build live dashboards that update as the agent executes steps.

Stream real-time AgentOps telemetry directly into your Vercel AI SDK frontend as your agents run.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect AgentOps (Agent Telemetry and Monitoring) MCP to Vercel AI SDK

Create your Vinkius account to connect AgentOps (Agent Telemetry and Monitoring) 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 AgentOps (Agent Telemetry and Monitoring) with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Inspect live traces in Vercel AI SDK

The `get_trace` tool pulls exact session sequences so your Next.js app can display step-by-step execution paths as they happen. We pass this data straight to `streamText`, letting your users watch the agent think, search, and execute without staring at a blank loading state. You feed the raw JSON payload from this MCP Server into your React components. This eliminates custom polling logic and keeps your edge functions fast since telemetry data flows over a single open connection.

Drill into active spans during streaming

The `get_span` tool isolates the exact execution block causing a delay or failure in your Vercel AI SDK stream. When a user flags a slow response, your app calls this tool to display the exact API call or DB query that stalled. Having this diagnostic data in the UI means you don't have to dig through terminal logs. Your frontend maps the span IDs directly to the active React component tree for instant debugging.

Render performance charts in your UI

The `get_trace_metrics` tool retrieves duration, cost, and token counts for active Vercel AI SDK runs. This MCP tool lets your Next.js dashboard display live cost tracking without delaying the main LLM response loop. By calling this over Vinkius, your Edge runtime stays lightweight. You avoid heavy SDK dependencies and get clean JSON metrics that map directly to your custom charts.

Setup guide

Set up AgentOps (Agent Telemetry and Monitoring) 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 AgentOps (Agent Telemetry and Monitoring) 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 AgentOps (Agent Telemetry and Monitoring) 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 AgentOps. 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 AgentOps (Agent Telemetry and Monitoring) 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 AgentOps (Agent Telemetry and Monitoring) MCP in Vercel AI SDK

Install `@ai-sdk/mcp` and use `createMCPClient` pointing to your Vinkius endpoint. Pass the tools array directly into `generateText` or `streamText` to let your agent fetch its own telemetry.

Yes, you pull trace data using `get_trace` and stream the raw metrics directly to your React components. This lets you build live dashboards that update as the agent executes steps.

Vinkius manages the underlying credentials so your edge functions don't need direct access to AgentOps API keys. You configure the connection once in Vinkius and use the single endpoint token in your SDK setup.

No, because the MCP Server runs in a sandboxed V8 isolate on Vinkius, ensuring sub-millisecond response times. Your UI streams the LLM output and telemetry concurrently without blocking the main thread.

Vinkius executes all requests in ephemeral, zero-trust sandboxes, meaning your trace data, span IDs, and project metrics are never stored on our servers. The connection acts as a secure pass-through directly to AgentOps.

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