How to Use the Treblle MCP in Vercel AI SDK

Q: How does Treblle help me observe API data using Vercel AI SDK?

Treblle's ingestapidata tool lets you send live API traffic to your agent. When paired with the Vercel AI SDK, this means you can stream those observability results directly into the user interface as they happen.

Q: Does Treblle support analyzing different types of API calls?

It does. The ingestapidata tool is designed to monitor and analyze general API traffic, handling both successful requests and error responses so your agent has a complete picture.

Stream real-time API observability into your UI with 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 Treblle MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Real-Time Data Streams for Streaming AI

The `ingest_api_data` tool sends request and response data directly to Treblle. This means your agent can pull live observability metrics that appear right in the user interface, not after a spinner loads up. You're building products where the end-user sees the AI working live. Using this MCP Server lets you stream those API calls as they happen, giving instant feedback on performance and data flow.

Masked Data for Secure Development

When calling `ingest_api_data`, Treblle automatically masks sensitive fields like passwords, CC numbers, and SSNs before transmission. You get the full context of a call—what happened—without ever exposing private user data. This is critical when building client-facing tools. It lets you document and analyze API traffic securely, keeping your users' information locked down while still providing deep insights.

Instant Visibility into API Traffic

The `ingest_api_data` tool helps you monitor and analyze API calls as they happen. You don't wait for batch processing; you get real-time data ingestion of both requests and responses. This immediate observability is key for frontends, especially those built with Vercel AI SDK. It means your agent can react to latency or specific error codes the instant it sees them.

Setup guide

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

Treblle's `ingest_api_data` tool lets you send live API traffic to your agent. When paired with the Vercel AI SDK, this means you can stream those observability results directly into the user interface as they happen.

Absolutely. The MCP Server masks sensitive fields—like passwords and SSNs—before sending them to your agent. This means you get the full context of API calls while keeping user data locked down.

It handles raw request and response data from your APIs, specifically documenting fields like passwords, CCs, and SSNs. The server masks these sensitive data types before it gets passed to your agent.

Yes. Because the tool ingests API traffic in real time, you get instant visibility into request and response data. This immediate feedback loop makes it perfect for streaming architectures like those used with the Vercel AI SDK.

It does. The `ingest_api_data` tool is designed to monitor and analyze general API traffic, handling both successful requests and error responses so your agent has a complete picture.

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