How to Use the Langfuse (LLM Tracing & Evals) MCP in Windsurf

Q: How does Windsurf use Langfuse (LLM Tracing & Evals) to debug failing agent runs?

Cascade calls gettrace to pull the exact execution graph of your LLM application directly into its context window. It then analyzes the step-by-step observations to pinpoint which prompt or model call broke, letting it write a fix immediately.

Q: Can I view prompt templates from Langfuse (LLM Tracing & Evals) inside Windsurf?

Yes, Cascade executes listprompts to fetch your active prompt templates directly. This allows the editor to run local checks and verify that your code matches the deployed prompt versions.

Q: How do I configure this MCP Server in my Windsurf setup?

Open your /.codeium/windsurf/mcpconfig.json file and add the server configuration under the mcpServers key. Alternatively, you can use the Settings UI under Cascade to add the connection with your Vinkius token.

Q: Can Windsurf retrieve aggregate cost metrics from Langfuse (LLM Tracing & Evals)?

Absolutely. Cascade calls getdailymetrics to retrieve rolled-up USD costs and latency statistics, helping you monitor operational spend directly from your editor.

Get production LLM debugging data straight to Cascade so Windsurf can fix broken prompts and trace execution paths automatically.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Langfuse (LLM Tracing & Evals) MCP to Windsurf

Create your Vinkius account to connect Langfuse (LLM Tracing & Evals) 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 Langfuse (LLM Tracing & Evals) with Windsurf

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Debug production LLM failures inside Windsurf Cascade

This MCP server lets Cascade use `get_trace` to pull the complete execution graph directly into your editor context. You don't need to copy-paste trace IDs from a web UI anymore when an API call fails. Cascade reads the trace structure, identifies the failing node, and uses `get_observation` to inspect the exact prompt and model parameters that caused the error. This lets the agent rewrite the failing code or prompt in one continuous flow.

Audit cost and latency spikes with this MCP Server

Tracking daily token usage and response times is critical, so the server exposes `get_daily_metrics` to give your agent instant access to operational costs. Cascade checks this data to flag sudden latency regressions or unexpected API spend without leaving the IDE. Once it spots a performance bottleneck, the agent chains `list_sessions` to trace the issue back to specific user flows. You get a clear picture of which sessions are burning your budget.

Pull and update prompt templates on the fly

Managing prompts directly in code gets messy, which is why the agent uses this MCP tool `list_prompts` to pull active templates managed inside Langfuse. Cascade compares your local code against the deployed prompt versions to ensure your app is running the correct system instructions. If a prompt needs tweaking, the agent can analyze past runs using `list_observations` to see how different versions performed. It makes prompt optimization a fast, local feedback loop.

Setup guide

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

mcp_config.json

{
  "mcpServers": {
    "langfuse-llm-tracing-evals-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 Langfuse. 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 Langfuse (LLM Tracing & Evals) 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 Langfuse (LLM Tracing & Evals) MCP in Windsurf

Cascade calls `get_trace` to pull the exact execution graph of your LLM application directly into its context window. It then analyzes the step-by-step observations to pinpoint which prompt or model call broke, letting it write a fix immediately.

Yes, Cascade executes `list_prompts` to fetch your active prompt templates directly. This allows the editor to run local checks and verify that your code matches the deployed prompt versions.

Open your `~/.codeium/windsurf/mcp_config.json` file and add the server configuration under the `mcpServers` key. Alternatively, you can use the Settings UI under Cascade to add the connection with your Vinkius token.

Absolutely. Cascade calls `get_daily_metrics` to retrieve rolled-up USD costs and latency statistics, helping you monitor operational spend directly from your editor.

Vinkius runs the server in an isolated, zero-trust sandbox where your LLM traces, observations, scores, and prompt templates are never cached or exposed to third parties. All communication between Windsurf and the MCP server is encrypted and temporary.

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