How to Use the LangSmith MCP in OpenAI Agents SDK

Q: Can my OpenAI Agents SDK system automatically fetch failed runs from LangSmith?

Yes, you can program your agent to query langsmithlistruns with a filter for failed status. It can then call langsmithgetrun to inspect the trace details and self-correct.

Q: Can I use this server to compare performance across different environments?

Yes, you can call langsmithlistprojects to pull metrics across staging and production environments. This gives you a clear view of latency and error rates.

Debug production deployments built with OpenAI Agents SDK using direct LangSmith telemetry via this MCP Server.

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 OpenAI Agents SDK

Create your Vinkius account to connect LangSmith to OpenAI Agents 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Debugging OpenAI Agents SDK with Live Traces

Your OpenAI agents make decisions in production, but you need to know exactly why a handoff failed. This MCP Server lets your agent inspect its own telemetry or pull execution data directly into your debugging workspace. By calling `langsmith_list_runs`, your development agent pulls raw execution times and status codes of recent actions. If a specialized agent gets stuck in a loop, you can immediately query `langsmith_get_run` to inspect the exact prompt payload that caused the failure.

Analyze Multi-Agent Projects

Grouping traces by project is the only way to make sense of complex agent systems. Use `langsmith_list_projects` to check which agent groups are lagging or costing too much money. Instead of guessing which model is slow, you get hard numbers on median latency and run counts. It keeps your production deployments lean and highlights exactly where execution costs spike.

Pinpoint Latency Regressions

When latency spikes, you can't waste time digging through generic cloud logs. You need to see the exact chain execution that stalled your agent. This is where `langsmith_list_runs` comes in. It pulls token consumption and status metrics directly so you can isolate the bottleneck before it hits your production users.

Setup guide

Set up LangSmith MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all LangSmith tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives LangSmith tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate LangSmith tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="LangSmith Agent",
            instructions="You have access to LangSmith tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Install the SDK and pass the MCP Server URL to your MCPServerStreamableHttpParams configuration. Your agent auto-discovers the tools, allowing it to execute `langsmith_list_projects` directly during a debug session.

Yes, you can program your agent to query `langsmith_list_runs` with a filter for failed status. It can then call `langsmith_get_run` to inspect the trace details and self-correct.

The tools only fetch telemetry data when explicitly called, so they don't slow down your main execution path. Set cacheToolsList to true in your MCP configuration to keep tool discovery fast.

Yes, you can call `langsmith_list_projects` to pull metrics across staging and production environments. This gives you a clear view of latency and error rates.

Your LangSmith traces, run details, and token counts are fetched through a secure V8 isolate sandbox on Vinkius. This MCP setup handles everything in memory and immediately discards the data, meaning nothing is ever written to disk.

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