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

Q: How do I query production costs using Helicone (LLM Observability) in Claude Desktop?

Ask Claude to run querycosts directly in your chat. The MCP integration securely communicates with Helicone's API to fetch your token spend logs, presenting a clean breakdown of your model expenses.

Q: Can I trace slow API calls with Helicone (LLM Observability) on Claude Desktop?

Yes, you can run querylatency inside your conversation to map out slow response times. Claude Desktop parses the raw performance array to show you exactly which LLM endpoints are lagging.

Q: Can I filter metrics by custom metadata tags?

Yes, you use listproperties to identify your custom tracking keys. Once Claude Desktop knows your active metadata arrays, you can filter costs and latency metrics by specific customer IDs or session tags.

Track LLM costs and latency directly inside Claude Desktop without leaving your chat window.

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 Claude Desktop

Create your Vinkius account to connect Helicone (LLM Observability) to Claude Desktop 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 Claude Desktop

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Inspect bottlenecks with Claude Desktop

`query_latency` pulls real-time performance metrics directly into your Claude Desktop chat window so you can spot slow model responses. Your agent analyzes these raw numbers to pinpoint exactly which middleware or model provider is dragging down your application's response times. This MCP Server connects your local workspace to Helicone's telemetry database. Instead of switching back and forth between browser tabs, you ask Claude to pull up the exact latency distribution for any model tag or routing path.

Track API spend using this MCP Server

`query_costs` extracts raw token expenses mapped directly to specific user accounts or organizational departments. Claude Desktop processes these financial logs to flag runaway loops or expensive system prompts before they drain your budget. Running `query_users` alongside cost queries lets your desktop agent isolate high-volume users. You get instant summaries of who is consuming the most resources, helping you make quick decisions on rate limits.

Compare prompt versions in Claude

`get_prompt_versions` pulls your historical prompt templates straight into your workspace to prevent regression issues. You can check what changed in your system instructions without digging through Git histories or manual text files. Combining this with `log_feedback` allows you to correlate specific prompt edits with actual user satisfaction scores. Claude Desktop maps these ratings so you can see if your latest prompt rewrite actually improved user interactions.

Setup guide

Set up Helicone (LLM Observability) MCP in Claude Web or Desktop

1

Open Claude Settings

Go to claude.ai, click your profile icon, then navigate to Customize → Connectors.
2

Add Custom Connector

Click the "+" button and select Add custom connector. Paste your Vinkius endpoint URL: https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. For OAuth-protected servers, expand Advanced settings to add credentials.
3

Start a conversation

Open a new chat. The Helicone (LLM Observability) MCP tools are available immediately — no restart needed.

Endpoint URL

https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

No configuration file needed — paste the URL directly in the Claude web interface.

Available on Free (1 connector), Pro, Max, Team, and Enterprise plans.

Prerequisites

Claude Desktop installed (macOS or Windows)
Active Vinkius subscription with a valid endpoint token

1

Open Claude Desktop Settings

Click the menu icon at the top-left corner, go to Settings → Developer → Edit Config. This opens claude_desktop_config.json in your default text editor.
2

Paste the Helicone (LLM Observability) MCP configuration

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

Restart Claude Desktop

Close and reopen the application. Claude needs a full restart to load new MCPs — refreshing a conversation is not enough.
4

Verify the connection

Open a new conversation. Click the 🔌 icon at the bottom of the message input. You should see tools listed under helicone-llm-observability-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 Claude Desktop

Ask Claude to run `query_costs` directly in your chat. The MCP integration securely communicates with Helicone's API to fetch your token spend logs, presenting a clean breakdown of your model expenses.

Yes, you can run `query_latency` inside your conversation to map out slow response times. Claude Desktop parses the raw performance array to show you exactly which LLM endpoints are lagging.

This MCP tool lets Claude analyze changes between versions and suggest optimizations based on past runs. You use `get_prompt_versions` to pull historical prompt configurations directly into your desktop workspace.

Yes, you use `list_properties` to identify your custom tracking keys. Once Claude Desktop knows your active metadata arrays, you can filter costs and latency metrics by specific customer IDs or session tags.

This MCP Server processes all telemetry, including raw prompt payloads and token costs, inside an isolated V8 sandbox. Claude Desktop never caches your sensitive logs locally, and Vinkius uses ephemeral execution environments to ensure your customer data is never stored or exposed to third parties.

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