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

Q: Can I use LangSmith (LLM Observability & Hub) in Cursor to find slow traces?

Yes, you can call listruns to see recent execution history and identify latency bottlenecks. Then, use getrun to inspect the specific timing data for a slow invocation. It makes finding performance issues straightforward.

Q: How does LangSmith (LLM Observability & Hub) show project boundaries in Cursor?

The listprojects tool maps out your distinct pipelines. You can use this to switch context between different services you monitor. It keeps your editor focused on the right project data.

Q: How do I verify prompt performance with LangSmith (LLM Observability & Hub) in Cursor?

You use listprompts to audit the current templates and compare them against historical performance in your traces. This helps you validate that changes improve your metrics. It bridges the gap between monitoring and development.

Debug your LLM code in Cursor by pulling live telemetry and trace data from LangSmith (LLM Observability & Hub) into your editor.

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 Cursor

Create your Vinkius account to connect LangSmith (LLM Observability & Hub) to Cursor 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 Cursor

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Inject live trace data into your code

Stop working with fake mock data. Use `list_runs` to grab actual production traces and let the AI generate code based on real-world inputs and outputs. When you need deeper insight into a specific failure, `get_run` provides the exact telemetry for that call. This allows you to write fixes that address real production edge cases.

Sync your prompt templates with Cursor

Grab your latest templates from the hub using `list_prompts` while you are writing code. This ensures your implementation always uses the correct, tested prompt structures. It removes the gap between your code and your monitoring. You see the template exactly as it exists in your production environment, preventing version mismatch errors.

Automate your evaluation workflow

Check your progress on evaluation tasks by calling `list_annotation_queues`. This keeps you updated on which model outputs require human review while you are busy writing new features. Use `list_datasets` to confirm your regression tests are ready. You can then trigger your evaluation pipelines knowing exactly which data is being tested against your code changes.

Setup guide

Set up LangSmith (LLM Observability & Hub) MCP in Cursor

Prerequisites

Cursor installed (macOS, Windows, or Linux)
Active Vinkius subscription with a valid endpoint token

1

Open MCP Settings

Go to Cursor Settings → MCP or open the Command Palette (Cmd+Shift+P / Ctrl+Shift+P) and search for "MCP: Add Server".
2

Add the LangSmith (LLM Observability & Hub) MCP

Cursor will create or open .cursor/mcp.json in your project root. Paste the JSON snippet on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Enable Agent mode

Open Composer (Cmd+I / Ctrl+I) and switch to Agent mode using the dropdown at the top. MCP tools are only available in Agent mode.
4

Verify the connection

Ask Cursor something like "List my recent LangSmith (LLM Observability & Hub) transactions." If the MCP tools are loaded correctly, Cursor will call the LangSmith (LLM Observability & Hub) tools automatically. You can also check Settings → MCP for a green status indicator.

.cursor/mcp.json

{
  "mcpServers": {
    "langsmith-llm-observability-hub-mcp": {
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

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 Cursor

Yes, you can call `list_runs` to see recent execution history and identify latency bottlenecks. Then, use `get_run` to inspect the specific timing data for a slow invocation. It makes finding performance issues straightforward.

The `list_projects` tool maps out your distinct pipelines. You can use this to switch context between different services you monitor. It keeps your editor focused on the right project data.

You can commit your configuration to the .cursor/mcp.json file. This ensures every developer on your team has access to the same observability tools. It keeps the team aligned on production data.

You use `list_prompts` to audit the current templates and compare them against historical performance in your traces. This helps you validate that changes improve your metrics. It bridges the gap between monitoring and development.

The tools interact with your LLM invocation records, which include prompt variables and model responses. You must ensure that sensitive user data is masked before it is sent to the observability platform. Treat these traces as production logs.

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