How to Use the LangSmith MCP in Windsurf

Q: How do I configure the LangSmith MCP Server in Windsurf?

Open /.codeium/windsurf/mcpconfig.json and add the server details under the mcpServers key. You can also use the Settings -> Cascade -> MCP Servers UI to connect it. Hit refresh and Cascade will auto-discover the tracing tools.

Connect the LangSmith MCP Server to Windsurf and let Cascade autonomously debug your LLM traces without writing a single script.

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 Windsurf

Create your Vinkius account to connect LangSmith to Windsurf 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 Windsurf

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Map Your LLM Projects in Windsurf

The `langsmith_list_projects` tool pulls your entire tracing architecture directly into the IDE. Cascade reads your project list, grabbing run counts, median latency stats, and feedback metrics in one pass. You don't have to switch contexts to figure out which environment is failing. Ask Cascade to check your production metrics, and it autonomously pulls the project data, spots the latency spikes, and tells you exactly where the bottlenecks live.

Autonomously Track Down Failed Runs

The `langsmith_list_runs` tool gives Cascade direct access to your recent LLM executions. It queries specific projects to pull run names, token usage, execution timing, and success rates. When your agent workflow breaks, Cascade chains this operation with your codebase. The agent pulls the last 50 failed runs, maps the error statuses to your local functions, and pinpoints the exact prompt that caused the chain to collapse.

Deep Dive into Specific MCP Server Traces

The `langsmith_get_run` tool extracts the granular payload of any individual LLM call. Cascade uses the trace ID to pull the exact inputs, outputs, and intermediate steps of a specific execution. Instead of manually clicking through a web dashboard, you just hand Cascade a broken trace ID. It fetches the run data, compares the token consumption against your limits, and rewrites the offending code block right in your editor.

Setup guide

Set up LangSmith MCP in Windsurf

Prerequisites

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

1

Open MCP configuration

Click the Cascade assistant icon in the sidebar, then click the hammer icon (🔨) at the top of the panel. Select "Configure" to open ~/.codeium/windsurf/mcp_config.json.
2

Add the LangSmith MCP

Paste the JSON snippet shown on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Refresh MCPs

Go back to the hammer icon (🔨) in Cascade and click "Refresh". Windsurf will detect the new server. No full restart is needed — the connection is hot-reloaded.
4

Verify in Cascade

Start a new Cascade conversation and ask something like "Show my LangSmith payment history." If connected, Cascade will call the LangSmith tools directly. You will see a green dot next to the server name in the MCP panel.

mcp_config.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 Windsurf

Open `~/.codeium/windsurf/mcp_config.json` and add the server details under the `mcpServers` key. You can also use the Settings -> Cascade -> MCP Servers UI to connect it. Hit refresh and Cascade will auto-discover the tracing tools.

Yes. Cascade calls the list projects tool to pull median latency and feedback counts. It reads the raw metrics and correlates them with your local code logic.

Context switching kills momentum. By bringing the traces into the IDE, Cascade reads the failing LLM inputs and immediately proposes code fixes, letting you skip the copy-pasting phase entirely.

You need to point it at a project first. Tell Cascade to check recent runs for errors, and it chains the necessary tools to find the exact trace ID that broke.

The V8 Isolate Sandbox ensures your granular LLM inputs, outputs, and token counts stay isolated during execution. This MCP connection is ephemeral, meaning trace payloads are read into memory to fix your code and immediately discarded.

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