How to Use the LangSmith MCP in Cursor

Q: How does Cursor use LangSmith traces to write better code?

Your Cursor agent pulls real execution payloads using langsmithgetrun. It then generates precise regression tests based on actual production failures.

Q: Can I list my LangSmith projects directly from the Cursor chat?

Yes, you can run langsmithlistprojects inside the editor's chat panel. Cursor retrieves your run counts and latency metrics to help you choose the right project context.

Q: How do I configure the LangSmith MCP Server for my Cursor project?

Add the server to your .cursor/mcp.json file in the project root. This makes the tools available to your agent whenever you open that workspace.

Q: Can I filter recent runs by status in the editor?

You can instruct your agent to filter the output of langsmithlistruns by success or error. This helps you isolate broken traces quickly.

Generate code against real production traces by connecting Cursor to your LangSmith 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 Cursor

Create your Vinkius account to connect LangSmith 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 with Cursor

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Debug Code Using Live Telemetry in Cursor

`langsmith_get_run` pulls the exact inputs and outputs of a failing production trace directly into your active editing session. Your Cursor agent writes unit tests based on the actual JSON payloads that caused your LLM to fail. This integration replaces placeholder test data with real-world failure cases.

Track Latency Regression While Coding

`langsmith_list_projects` exposes aggregate metrics inside your code editor to show how code changes impact performance. You compare your current local latency against production baselines without switching windows. Running this MCP Server in Cursor lets your agent flag projects with high error rates.

Pull Recent Traces Into Cursor Agent Mode

`langsmith_list_runs` lists the most recent executions from any project inside your editor sidebar. Your agent scans these runs to identify token spikes or unexpected model outputs. You can immediately select a run ID to inspect its detailed trace.

Setup guide

Set up LangSmith 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 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 transactions." If the MCP tools are loaded correctly, Cursor will call the LangSmith tools automatically. You can also check Settings → MCP for a green status indicator.

.cursor/mcp.json

{
  "mcpServers": {
    "langsmith-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 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 Cursor

Your Cursor agent pulls real execution payloads using `langsmith_get_run`. It then generates precise regression tests based on actual production failures.

Yes, you can run `langsmith_list_projects` inside the editor's chat panel. Cursor retrieves your run counts and latency metrics to help you choose the right project context.

Add the server to your `.cursor/mcp.json` file in the project root. This makes the tools available to your agent whenever you open that workspace.

You can instruct your agent to filter the output of `langsmith_list_runs` by success or error. This helps you isolate broken traces quickly.

No, all communication between Cursor and LangSmith is direct and encrypted. Your trace payloads and API credentials never pass through external intermediate 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