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

Q: How does Windsurf use LangSmith (LLM Observability & Hub) to debug failing LLM calls?

Cascade uses the listruns tool to fetch recent execution logs and getrun to pinpoint the exact step that failed. It reads the raw inputs and outputs directly, allowing it to rewrite your local code or prompt templates instantly to fix the bug.

Q: Can Cascade pull production prompt templates using LangSmith (LLM Observability & Hub) inside Windsurf?

Yes, this integration lets Cascade invoke listprompts to pull templates directly from your hub. It can then analyze these templates against your local implementation to ensure you are using the correct variables.

Q: How do I configure this MCP Server for LangSmith (LLM Observability & Hub) in my Windsurf setup?

You can edit your local /.codeium/windsurf/mcpconfig.json file or use the Settings UI under Cascade to add the server. Once connected, Cascade automatically discovers the six tools and starts using them during debugging sessions.

Q: Can I inspect my LangSmith project boundaries with this tool?

Yes, the listprojects tool maps out the boundaries of your active tracing sessions. This allows Cascade to understand which pipeline it is currently debugging and filter runs accordingly.

Debug live AI chains directly in Windsurf with prompt-level traces and dataset tracking.

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 Windsurf

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Trace live runs inside Windsurf

The `list_runs` tool isolates the raw interactions containing prompts sent to and responses received from the AI models. Let's face it: tracing LLM calls is usually a pain. When Cascade runs into a prompt failure, it uses this MCP Server to pull the exact inputs and outputs of your execution tree. No more digging through browser tabs to find where your chain broke. Once the agent gets the run list, it calls `get_run` to extract the precise telemetry for that single LLM invocation run. Cascade reads this data, spots the hallucination or the bad system prompt, and fixes your code on the fly. You see the fix before you even realize the API returned garbage.

Manage prompt templates via Windsurf MCP Server

The `list_prompts` tool extracts prompt templates hosted in the LangChain Hub directly into your workspace. Instead of copying and pasting templates from a browser UI, Cascade pulls them straight into your active context. It lets you inspect versioned prompts and swap variables without leaving your editor. After grabbing the template, Cascade checks your active tracing environments using `list_projects` to map out the boundaries of distinct AI pipelines currently monitored by LangSmith. This keeps your local development prompts perfectly aligned with the target project environment. You write cleaner code because your agent knows exactly which version of the prompt is live.

Audit evaluation datasets and human queues

The `list_datasets` tool lists all evaluation and fine-tuning datasets mapped in LangSmith to verify your test suites. When you want to run regression tests, Cascade checks these datasets to see what test cases are available. It gives your agent the exact data it needs to run evaluations against your local code changes. To keep humans in the loop, the agent uses `list_annotation_queues` to inspect active human-in-the-loop annotation queues. This lets Cascade find which outputs need manual review and flag them for your team. You get a direct line from production data to your local testing environment.

Setup guide

Set up LangSmith (LLM Observability & Hub) 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 (LLM Observability & Hub) 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 (LLM Observability & Hub) payment history." If connected, Cascade will call the LangSmith (LLM Observability & Hub) tools directly. You will see a green dot next to the server name in the MCP panel.

mcp_config.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 Windsurf

Cascade uses the `list_runs` tool to fetch recent execution logs and `get_run` to pinpoint the exact step that failed. It reads the raw inputs and outputs directly, allowing it to rewrite your local code or prompt templates instantly to fix the bug.

Yes, this integration lets Cascade invoke `list_prompts` to pull templates directly from your hub. It can then analyze these templates against your local implementation to ensure you are using the correct variables.

You can edit your local `~/.codeium/windsurf/mcp_config.json` file or use the Settings UI under Cascade to add the server. Once connected, Cascade automatically discovers the six tools and starts using them during debugging sessions.

Yes, the `list_projects` tool maps out the boundaries of your active tracing sessions. This allows Cascade to understand which pipeline it is currently debugging and filter runs accordingly.

Your raw LLM runs, prompts, and evaluation datasets are protected because Vinkius runs this MCP connector inside a secure, zero-trust V8 Isolate sandbox. The data flows directly between your local Windsurf client and the LangSmith API endpoint without intermediate storage.

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