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

Q: How do I analyze LLM latency using Helicone (LLM Observability) inside Cursor?

Run querylatency inside Cursor's Composer or Chat panel to pull live performance metrics. This MCP tool processes the latency data to help you identify which parts of your code are causing slow model responses.

Q: Can Cursor use Helicone (LLM Observability) to automatically optimize my prompt files?

Yes, Cursor can call getpromptversions to inspect your production prompt configurations. The editor then compares these templates with your local source files to suggest optimizations based on historical performance.

Q: How do I track down failing LLM chains with Helicone (LLM Observability) in Cursor?

Ask Cursor to execute querysessions to fetch the complete trace of a failing run. The Cursor MCP setup fetches the complete trace so the AI agent can read the session logs and locate the exact step where your code failed.

Q: Can I query custom tracking properties?

Yes, you run listproperties to see what metadata tags are currently active in your production telemetry. Cursor uses this list to filter your cost and usage queries by specific test environments or features.

Generate code using live Helicone latency and cost metrics directly inside your Cursor editor.

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 Cursor

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Optimize code blocks with Cursor and Helicone

`query_costs` fetches real-time API spend metrics directly into your Cursor editor. The AI agent uses this financial data to refactor your code, choosing cheaper model alternatives or optimizing prompt payloads right where you write your code. This MCP Server allows your editor to analyze token consumption trends without manual exports. You can instantly see which functions cost the most and rewrite them to use more efficient formatting.

Trace active user sessions using this MCP Server

`query_sessions` extracts multi-turn conversation traces directly into Cursor's chat panel to help you debug complex agentic workflows. Your editor parses these structured session rules to pinpoint where a multi-step LLM chain failed or looped. Having these raw trace logs inside your development environment means you can write fixes immediately. You do not need to copy-paste JSON logs from an external web dashboard when debugging a failing production run.

Sync prompt versions directly to your codebase

`get_prompt_versions` retrieves the exact version history of your deployed prompt templates. Cursor compares these production strings against your local application code to prevent deployment mismatches. Using `query_prompts` alongside this tool lets you inspect exactly what instructions your application sent during recent runs. You can rapidly iterate on your prompt files and test them against live telemetry data.

Setup guide

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

.cursor/mcp.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 Cursor

Run `query_latency` inside Cursor's Composer or Chat panel to pull live performance metrics. This MCP tool processes the latency data to help you identify which parts of your code are causing slow model responses.

Yes, Cursor can call `get_prompt_versions` to inspect your production prompt configurations. The editor then compares these templates with your local source files to suggest optimizations based on historical performance.

Ask Cursor to execute `query_sessions` to fetch the complete trace of a failing run. The Cursor MCP setup fetches the complete trace so the AI agent can read the session logs and locate the exact step where your code failed.

Yes, you run `list_properties` to see what metadata tags are currently active in your production telemetry. Cursor uses this list to filter your cost and usage queries by specific test environments or features.

Your raw prompts and payloads fetched via this MCP Server are processed inside Vinkius's secure, ephemeral V8 isolates. Cursor connects to this server using a single secure token, ensuring that sensitive production logs never touch local storage or persistent external databases.

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