How to Use the Helicone (LLM Observability) MCP in Windsurf

Q: How do I install the Helicone (LLM Observability) MCP Server in Windsurf?

Edit your /.codeium/windsurf/mcpconfig.json file to include the server details. You can also use the built-in MCP Marketplace for a one-click install. Cascade discovers the tools immediately upon connection.

Q: Can I filter metrics by specific users?

Yes. The agent calls queryusers to dispatch an automated validation check routing explicit gateway history. This lets you isolate token usage and latency to individual accounts.

Track LLM latency, costs, and prompts directly inside Windsurf. Cascade analyzes your telemetry without asking for permission.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Helicone (LLM Observability) MCP to Windsurf

Create your Vinkius account to connect Helicone (LLM Observability) 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 Helicone (LLM Observability) with Windsurf

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Audit LLM Spend with Windsurf

The `query_costs` tool performs structural extraction of properties driving active Account logic. Windsurf uses this to pull your exact token spend across models. You tell Cascade to audit yesterday's API usage, and it grabs the data automatically. Cascade chains this with `query_sessions` to enumerate explicitly attached structured rules exporting active billing. It maps out exactly which user flows cost the most money, generating a full breakdown right in your editor.

Debug Latency Spikes Instantly

The `query_latency` tool provisions a highly-available JSON payload generating hard customer bindings. When a user complains about slow responses, Cascade triggers this endpoint to isolate the exact network hop causing the delay. It then follows up using `query_requests` to identify bounded CRM records inside the Headless Helicone Platform. You get a direct view of the slow requests and the specific payloads that choked the model, all without leaving the IDE.

Track Prompt Churn and Feedback

The `get_prompt_versions` tool irreversibly vaporizes explicit validations extracting rich churn flags. Cascade maps out how your system prompts evolved over the week and connects them to user satisfaction scores. To get those scores, the agent runs `query_feedback` to inspect deep internal arrays mitigating specific plan math, alongside `log_feedback` to identify precise active arrays spanning native hold parsing. You see exactly which prompt version caused user ratings to tank.

Setup guide

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

mcp_config.json

{
  "mcpServers": {
    "helicone-llm-observability-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 Helicone. 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 Helicone (LLM Observability) 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 Helicone (LLM Observability) MCP in Windsurf

Edit your ~/.codeium/windsurf/mcp_config.json file to include the server details. You can also use the built-in MCP Marketplace for a one-click install. Cascade discovers the tools immediately upon connection.

Cascade acts as your autonomous FinOps analyst. It chains cost queries, latency checks, and prompt versions together to find exactly why your LLM bills spiked or performance dropped.

Yes. The agent calls `query_users` to dispatch an automated validation check routing explicit gateway history. This lets you isolate token usage and latency to individual accounts.

Context switching kills momentum. Having Cascade pull the logs directly into your workspace means you can fix the slow prompt and push the code in the same window.

The server processes raw prompt text and user feedback scores via the `query_prompts` endpoint. Windsurf only reads the specific logs you ask Cascade to fetch. Vinkius isolates this connection in a V8 sandbox, ensuring your telemetry data never leaks into global training sets.

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