How to Use the LangSmith (LLM Observability & Hub) MCP in OpenAI Agents SDK

Q: Can the OpenAI Agents SDK automatically discover these LangSmith tools?

Yes. The SDK auto-discovers all six MCP tools, from getrun to listprompts. Set cacheToolsList=True to speed up initialization in your production environment.

Connect LangSmith (LLM Observability & Hub) to the OpenAI Agents SDK to trace LLM calls, manage prompt templates, and debug production pipelines.

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 OpenAI Agents SDK

Create your Vinkius account to connect LangSmith (LLM Observability & Hub) 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 (LLM Observability & Hub) with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Debug pipelines with this MCP Server

The `list_projects` tool maps out the boundaries of distinct AI pipelines currently monitored by LangSmith. Your OpenAI agent uses this to find the correct project context before digging into specific telemetry. Once it has the project, the agent calls `list_runs` to isolate the raw interactions containing prompts sent to and responses received from the AI models. If a specific step failed, it fires `get_run` to extract the precise telemetry for that single LLM invocation.

Audit Hub prompt templates

The `list_prompts` tool extracts prompt templates hosted in the LangChain Hub directly into your agent's context. Your OpenAI agent reads these templates to verify that the deployed prompts match your strict safety constraints. You do not have to guess what instructions the model actually received in production. The agent pulls the exact template version and cross-references it with the guardrails you configured in the OpenAI dashboard.

Manage evaluation data

The `list_datasets` tool lets your agent list all evaluation and fine-tuning datasets mapped in LangSmith. It pulls these records to check if your latest handoff logic degraded performance against your baseline data. If the agent needs human feedback, it checks `list_annotation_queues`. This lists active human-in-the-loop annotation queues so your developers know exactly which runs require manual review before the next deployment.

Setup guide

Set up LangSmith (LLM Observability & Hub) 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 (LLM Observability & Hub) tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives LangSmith (LLM Observability & Hub) 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 (LLM Observability & Hub) 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 (LLM Observability & Hub) Agent",
            instructions="You have access to LangSmith (LLM Observability & Hub) 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 (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 OpenAI Agents SDK

Install the openai-agents package via pip. Create an MCPServerStreamableHttp instance with your endpoint URL, then pass it as mcp_servers=[server] to your Agent constructor.

Yes. The SDK auto-discovers all six MCP tools, from get_run to list_prompts. Set cacheToolsList=True to speed up initialization in your production environment.

LangSmith gives you cross-platform visibility if you route calls outside OpenAI. You can pull evaluation data with list_datasets and audit external prompt templates right from your agent.

No. This integration only reads data. Your agent can fetch telemetry and list active projects, but it cannot write new traces or modify your prompt templates.

It reads raw LLM invocation traces and prompt templates directly from your LangSmith account. Vinkius runs this MCP Server in a zero-trust, ephemeral V8 Isolate Sandbox. The server authenticates with a single endpoint token and leaves no residual data after your agent disconnects.

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