How to Use the LangSmith MCP in Mastra AI

Q: How can my Mastra AI agent retry a step if LangSmith shows an error?

In your workflow, check the status from a langsmithlistruns or langsmithgetrun call. If the status is 'error', use Mastra AI's built-in conditional logic to trigger a retry branch. It's a classic pattern for building resilient agents.

Q: Can I use LangSmith to trigger alerts from a Mastra AI workflow?

Yes, that's a primary use case. Have your agent call langsmithlistruns on a schedule. If it finds too many errors or latency spikes, it can use another tool to send a Slack message or create a ticket.

Q: How does Mastra AI find the right LangSmith project to query?

Your agent can call langsmithlistprojects first to get a list of all available projects and their IDs. Then it can find the one it needs by name and use that ID for subsequent calls to langsmithlistruns.

Build self-healing workflows in Mastra AI. Automatically pull LangSmith traces from this MCP server to debug and retry failed agent steps.

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 Mastra AI

Create your Vinkius account to connect LangSmith to Mastra AI 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 Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate Failure Analysis

The `langsmith_get_run` tool is your go-to for root cause analysis inside a Mastra AI workflow. When a step fails, your workflow can automatically trigger this tool with the run ID to pull the full trace. You get the exact error, latency, and context without manual digging. This turns debugging from a reactive task into a proactive, automated step. Set up a conditional branch in your agent: if a run fails, call `langsmith_get_run`, log the details to Datadog, and then decide whether to retry or escalate. It's observability as code.

Monitor Project Performance

With `langsmith_list_runs`, your Mastra AI agent can periodically check the health of a production system. Schedule a workflow to run every five minutes, list recent runs, and check for an unusual number of errors or high latency. If your agent detects a problem—say, more than 5% of runs have failed in the last hour—it can trigger an alert or open an incident. This isn't just monitoring; it's an automated response system built on real performance data from your LangSmith MCP Server.

Your Mastra AI Agent's Observability Layer

Use the `langsmith_list_projects` tool at the start of a complex workflow to get a baseline. Your Mastra AI agent can check the current median latency and error rates for a project before it starts a batch job. This gives your agent context. If the system is already degraded, it might choose a different path, delay execution, or notify an admin. It’s how you build smart workflows that adapt to the current state of your stack, powered by this MCP Server.

Setup guide

Set up LangSmith MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All LangSmith tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "langsmith-mcp-client",
  servers: {
    "langsmith-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "LangSmith Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to LangSmith tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent LangSmith transactions"
);
console.log(result.text);

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 Mastra AI

In your workflow, check the status from a `langsmith_list_runs` or `langsmith_get_run` call. If the status is 'error', use Mastra AI's built-in conditional logic to trigger a retry branch. It's a classic pattern for building resilient agents.

Yes, that's a primary use case. Have your agent call `langsmith_list_runs` on a schedule. If it finds too many errors or latency spikes, it can use another tool to send a Slack message or create a ticket.

Your agent can call `langsmith_list_projects` first to get a list of all available projects and their IDs. Then it can find the one it needs by name and use that ID for subsequent calls to `langsmith_list_runs`.

Simplicity and security. The MCP server gives you a single, authenticated endpoint managed by Vinkius. You don't have to bundle SDKs, manage API keys in your agent's environment, or worry about dependency updates.

It only handles your LangSmith project and run metadata—that means trace IDs, status codes, and performance numbers like latency and token usage. Your actual LLM prompts and completions are not processed or stored by the server. Each request is stateless and runs in a new, zero-trust container.

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