How to Use the LangSmith (LLM Observability & Hub) MCP in Vercel AI SDK

Q: How do I fetch live run data using LangSmith (LLM Observability & Hub) in a Vercel AI SDK project?

You use listruns to grab the recent execution traces directly from your Next.js API route using the MCP protocol. The Vercel AI SDK handles the stream, letting you map the raw token inputs and outputs directly to your UI components without writing custom polling code.

Q: Can I use LangSmith (LLM Observability & Hub) prompt templates inside my Vercel AI SDK edge functions?

Yes. This MCP Server exposes listprompts to pull your templates straight into your edge functions. You pass the retrieved templates directly to generateText or streamText to keep your prompts decoupled from your frontend codebase.

Q: How does LangSmith (LLM Observability & Hub) help me debug slow runs in my Vercel AI SDK app?

The getrun tool retrieves the exact latency and execution steps of any run. Your Vercel AI SDK application can display this performance breakdown in a developer dashboard, showing you exactly which LLM call caused the slowdown.

Debug production traces and render LangSmith data directly inside your Vercel AI SDK frontend in real time.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect LangSmith (LLM Observability & Hub) MCP to Vercel AI SDK

Create your Vinkius account to connect LangSmith (LLM Observability & Hub) 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 LangSmith (LLM Observability & Hub) with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream live LLM traces to your Vercel AI SDK frontend

`list_runs` fetches the raw inputs and outputs of your active LLM calls so your React or Next.js app can display live execution logs. You bypass the slow backend polling loops and let your users watch their agent's step-by-step thinking settle on the screen. Combining this with `get_run` lets you pull exact token counts and latency metrics for any single execution. Your Vercel AI SDK client renders these details in a custom debugging panel, giving your users instant feedback on why a response took three seconds instead of one.

Pull version-controlled prompts directly into Edge Functions

`list_prompts` fetches your prompt templates stored in the LangChain Hub and feeds them directly into `streamText`. You don't have to redeploy your Next.js application just to tweak a system instruction or adjust a raw variable. This MCP Server integration allows your edge runtime to pull the latest prompt version on the fly. Your Vercel AI SDK app stays lightweight, pulling templates dynamically while keeping your API keys safe inside Vinkius's secure sandboxed environment.

Audit active pipelines with real-time project mapping

`list_projects` maps out the active tracing pipelines so you can switch between staging and production environments directly from your UI. Your frontend developers get immediate access to project structures without logging into a separate cloud console. When combined with `list_datasets`, this tool lets your Vercel AI SDK app pull evaluation test suites straight into your local development server. You run your regression tests locally and stream the results back to your dashboard instantly.

Setup guide

Set up LangSmith (LLM Observability & Hub) 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 LangSmith (LLM Observability & Hub) 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 LangSmith (LLM Observability & Hub) 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 LangSmith. 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 LangSmith (LLM Observability & Hub) 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 LangSmith (LLM Observability & Hub) MCP in Vercel AI SDK

You use `list_runs` to grab the recent execution traces directly from your Next.js API route using the MCP protocol. The Vercel AI SDK handles the stream, letting you map the raw token inputs and outputs directly to your UI components without writing custom polling code.

Yes. This MCP Server exposes `list_prompts` to pull your templates straight into your edge functions. You pass the retrieved templates directly to `generateText` or `streamText` to keep your prompts decoupled from your frontend codebase.

The `get_run` tool retrieves the exact latency and execution steps of any run. Your Vercel AI SDK application can display this performance breakdown in a developer dashboard, showing you exactly which LLM call caused the slowdown.

Yes, this MCP tool lets you view and select evaluation datasets. You can pull these test cases straight into your local test scripts to run evaluations against your Vercel AI SDK endpoints.

Your telemetry data flows securely through Vinkius's isolated V8 sandboxes directly to your private endpoint. The MCP Server never stores your prompt variables or execution traces, ensuring complete data isolation.

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