How to Use the LangSmith MCP in Vercel AI SDK

Q: How do I use LangSmith with the Vercel AI SDK to see recent traces?

Connect the LangSmith MCP Server to your createMCPClient instance. Then, your agent can call langsmithlistruns and stream the results directly into your UI components. It's the fastest way to get observability data into your Next.js or React app.

Q: Can my Vercel AI SDK app show LangSmith project stats?

Yes. The langsmithlistprojects tool is designed for this. Your agent can call it to get run counts and latency metrics, which you can then render into a live dashboard in your user interface.

Stream real-time LangSmith trace data directly into your Vercel AI SDK frontends. No more loading spinners for observability.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect LangSmith MCP to Vercel AI SDK

Create your Vinkius account to connect LangSmith 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 with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Debug Runs Directly in Your UI

The `langsmith_get_run` tool pulls a specific trace's details right into your application. When a user reports a weird AI response, you can give them a button to fetch the exact trace and see what happened under the hood—latency, token counts, the whole nine yards. Because you're using the Vercel AI SDK, this data streams directly into your React or Next.js components. The user sees the diagnostic info appear line-by-line, not after a five-second wait. It makes debugging feel interactive, not like a chore.

Build Live Project Health Dashboards

Use `langsmith_list_projects` to build a live monitoring dashboard inside your own app. It gives you a top-level view of all your LLM projects, complete with run counts and median latency, straight from LangSmith. Imagine an internal admin panel where your team can watch project health in real time. As new runs complete, your Vercel AI SDK-powered UI updates automatically. You can spot a spike in latency across a project without ever leaving your application.

Stream Recent Traces with This MCP Server

The `langsmith_list_runs` tool gives your UI a direct feed of the latest LLM runs for any project. You can build a 'Recent Activity' feed that shows the status, token usage, and timing for every agent action as it happens. This isn't just a static list. Hooked into the Vercel AI SDK, each run's data can be streamed and rendered incrementally. This MCP Server makes it possible to show users a live ticker of AI operations, proving the system is working and giving them immediate insight.

Setup guide

Set up LangSmith 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 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 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 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 MCP in Vercel AI SDK

Connect the LangSmith MCP Server to your `createMCPClient` instance. Then, your agent can call `langsmith_list_runs` and stream the results directly into your UI components. It's the fastest way to get observability data into your Next.js or React app.

Yes. The `langsmith_list_projects` tool is designed for this. Your agent can call it to get run counts and latency metrics, which you can then render into a live dashboard in your user interface.

Absolutely. Just get the run ID for the bad response. Your agent can then use the `langsmith_get_run` tool to fetch all the trace details and display them, giving you or your user instant context on the failure.

Vinkius handles the auth and hosting for you. You get one endpoint token and you're done. Plus, the server is sandboxed and ephemeral, so you're not managing infrastructure or worrying about credential leaks.

This server only interacts with your LangSmith trace and project metadata—things like run IDs, latency, and token counts. It never accesses the raw inputs or outputs of your LLM calls. All connections are over TLS, and the Vinkius platform runs each request in an isolated sandbox.

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