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

Q: How do I inspect failed workflow steps using LangSmith (LLM Observability & Hub) in Mastra AI?

You use listruns to pull the recent execution history of your workflow steps. Mastra AI agents can analyze these traces to identify which specific conditional branch failed and why.

Q: Can Mastra AI workflows dynamically pull prompts from LangSmith (LLM Observability & Hub)?

Yes. The listprompts tool allows your Mastra AI workflows to fetch prompt templates directly from the Hub, letting your agents update their system instructions on the fly without a code push.

Q: How does LangSmith (LLM Observability & Hub) handle human-in-the-loop validation in Mastra AI?

The listannotationqueues tool lets your Mastra AI workflow check for active human review queues. Your workflow can pause execution until a human logs in and approves the pending run.

Feed real-time LangSmith trace data and prompt templates directly into your Mastra AI workflow engine.

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 Mastra AI

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Debug complex Mastra AI workflow branches in real time

`list_runs` isolates the exact execution traces of your multi-step Mastra AI workflows so you can see where a conditional branch failed. You don't have to guess why a retry logic failed when you can inspect the raw input payload directly. This MCP Server provides `get_run` to drill down into specific step failures. Mastra AI agents use this run telemetry to dynamically adjust their retry backoffs or trigger fallback steps when an external API times out.

Inject versioned prompts into autonomous agent workflows

`list_prompts` retrieves your latest prompt templates from the LangChain Hub and feeds them to your Mastra AI agents. Your agents can swap their own system instructions mid-run based on the workflow state, without requiring a redeployment. By using this MCP Server, your workflow engine stays synchronized with your team's prompt designers. The moment a prompt is updated in the Hub, your autonomous agents begin using the new template on their next run.

Manage human-in-the-loop loops with active queues

`list_annotation_queues` reveals the active human-in-the-loop queues currently waiting for feedback in your project. Your Mastra AI workflows query these queues to halt autonomous execution until a human reviewer approves the output. Combined with `list_datasets`, your agents can automatically route flagged runs into evaluation datasets. This feedback loop ensures that edge cases discovered during autonomous runs are preserved for future regression testing.

Setup guide

Set up LangSmith (LLM Observability & Hub) 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 (LLM Observability & Hub) 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-llm-observability-hub-mcp-client",
  servers: {
    "langsmith-llm-observability-hub-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

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

const result = await agent.generate(
  "List recent LangSmith (LLM Observability & Hub) 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 (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 Mastra AI

You use `list_runs` to pull the recent execution history of your workflow steps. Mastra AI agents can analyze these traces to identify which specific conditional branch failed and why.

Yes. The `list_prompts` tool allows your Mastra AI workflows to fetch prompt templates directly from the Hub, letting your agents update their system instructions on the fly without a code push.

The `list_annotation_queues` tool lets your Mastra AI workflow check for active human review queues. Your workflow can pause execution until a human logs in and approves the pending run.

You instantiate the MCP client pointing to the secure Vinkius URL and pass `mcpClient.listTools()` into your agent's tools array. The agent can then call any of the six observability tools autonomously.

This MCP Server processes your human feedback queues and evaluation datasets entirely in memory within Vinkius's ephemeral V8 sandboxes. No trace data or human annotations are cached or written to persistent disk on our servers.

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