How to Use the Helicone (LLM Observability) MCP in VS Code Copilot

Q: Can I track production costs using Helicone (LLM Observability) in VS Code Copilot?

Yes, your team can execute querycosts within the chat interface. VS Code Copilot uses this MCP integration to fetch your live token spend metrics, allowing you to monitor API expenses without leaving your workspace.

Q: How do I debug slow LLM responses with Helicone (LLM Observability) on VS Code Copilot?

Ask Copilot to run querylatency to pull the latest latency distributions. The assistant analyzes these production metrics to help you find and fix bottlenecks in your API calls.

Q: Can we inspect prompt history using Helicone (LLM Observability) inside VS Code Copilot?

Yes, you run getpromptversions to pull historical prompt configurations directly into the editor. This MCP tool lets your team compare changes and ensure your code matches the active production templates.

Q: How do I filter my observability data by specific users?

Use queryusers to pull user-level metrics directly into the editor. Copilot can then group your latency and cost data by user ID to help you find which accounts are experiencing issues.

Monitor team-wide LLM performance and costs using VS Code Copilot with zero dashboard context-switching.

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 VS Code Copilot

Create your Vinkius account to connect Helicone (LLM Observability) to VS Code Copilot 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 VS Code Copilot

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Audit API spend using this MCP Server in VS Code

`query_costs` brings production spend metrics directly into your VS Code Copilot chat window. Your team can run queries to see which features or microservices are driving up your bills. This setup keeps everyone on the same page regarding API budgets without sharing raw credentials. The editor formats the cost data so you can quickly spot anomalies during your daily standup or code review.

Diagnose latency issues inside VS Code Copilot

`query_latency` pulls real-time performance profiles for your LLM calls. VS Code Copilot uses these raw latency metrics to help you write smarter fallback logic or choose faster model endpoints for time-sensitive features. This MCP Server supplies concrete numbers directly inside your workspace. You can immediately refactor your async handlers or connection timeouts based on real-world response times.

Inspect user feedback directly in VS Code

`query_feedback` retrieves actual user-submitted ratings and comments associated with your LLM generations. VS Code Copilot maps these feedback arrays against your code to help you identify which prompt versions are frustrating your users. Running `query_requests` alongside feedback queries lets your team inspect the exact prompts that led to negative ratings. You can modify your application's system instructions right away to address user complaints.

Setup guide

Set up Helicone (LLM Observability) MCP in VS Code Copilot

Prerequisites

VS Code 1.99 or later with GitHub Copilot extension
Active Vinkius subscription with a valid endpoint token

1

Open MCP configuration

Open the Command Palette (Cmd+Shift+P / Ctrl+Shift+P) and run "MCP: Add Server". Select HTTP (Streamable) as the server type. VS Code will create .vscode/mcp.json in your workspace.
2

Add the Helicone (LLM Observability) MCP

Paste the JSON snippet shown on the right into your .vscode/mcp.json. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Switch to Agent mode

Open Copilot Chat (Cmd+Shift+I / Ctrl+Shift+I) and switch to Agent mode using the dropdown. MCP tools are only available in Agent mode — they do not appear in Edit or Ask modes.
4

Verify the connection

In the Copilot Chat input, type # to list available tools. You should see the Helicone (LLM Observability) tools listed. Try asking: "List my recent Helicone (LLM Observability) transactions" and Copilot will invoke them automatically.

.vscode/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 VS Code Copilot

Yes, your team can execute `query_costs` within the chat interface. VS Code Copilot uses this MCP integration to fetch your live token spend metrics, allowing you to monitor API expenses without leaving your workspace.

Ask Copilot to run `query_latency` to pull the latest latency distributions. The assistant analyzes these production metrics to help you find and fix bottlenecks in your API calls.

Yes, you run `get_prompt_versions` to pull historical prompt configurations directly into the editor. This MCP tool lets your team compare changes and ensure your code matches the active production templates.

Use `query_users` to pull user-level metrics directly into the editor. Copilot can then group your latency and cost data by user ID to help you find which accounts are experiencing issues.

All request payloads accessed via this MCP Server are securely routed through Vinkius's zero-trust V8 sandbox. VS Code Copilot uses a single endpoint token to execute these queries, preventing sensitive prompt data or API keys from being cached or stored in your local workspace.

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