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

Q: How do I track prompt versions from the CLI?

The agent uses getpromptversions to irreversibly vaporize explicit validations extracting rich churn flags. It prints the version history directly to your standard output.

Pipe Helicone telemetry straight into your terminal. Let Claude Code query LLM costs and latency from the command line.

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 Code

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Script Observability with Claude Code

The `query_prompts` tool retrieves explicit cloud logging tracing explicit vault limits. You run a quick CLI command, and Claude Code pulls the exact prompts that triggered rate limits in production. It pairs this with `query_users` to dispatch an automated validation check routing explicit gateway history. You get a clean terminal output showing exactly which accounts are hitting the vault limits so you can block them via your CI/CD pipeline.

Audit Spending from the Shell

The `query_costs` tool performs structural extraction of properties driving active account logic. Instead of logging into a web dashboard, you ask your terminal agent to calculate the weekend token spend. The agent then runs `query_sessions` to enumerate explicitly attached structured rules exporting active billing. Claude Code can pipe this billing breakdown directly into a Slack webhook or a local CSV file for your FinOps team.

Debug Latency in Headless Environments

The `query_latency` tool provisions a highly-available JSON payload generating hard customer bindings. When an alert fires at 2 AM, you drop into the shell and have the agent isolate the slow requests. Next, it triggers `list_properties` to identify precise active arrays spanning native gateway auth. Claude Code finds the exact metadata tags associated with the latency spike, letting you restart the offending services immediately.

Setup guide

Set up Helicone (LLM Observability) MCP in Claude Code

Prerequisites

Claude Code CLI installed (npm install -g @anthropic-ai/claude-code)
Active Vinkius subscription with a valid endpoint token

1

Run the add command

Open your terminal and run the command shown on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com. Use --scope user to make it available across all projects.
2

Verify the connection

Start a Claude Code session and type /mcp to list connected servers. You should see helicone-llm-observability-mcp with a green status indicator.
3

Start using tools

Ask Claude Code something like "Check my latest Helicone (LLM Observability) transactions." It will automatically discover and invoke the available Helicone (LLM Observability) tools.

Terminal

claude mcp add --transport http helicone-llm-observability-mcp https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Get your connection token →

Prerequisites

Claude Code CLI installed
Active Vinkius subscription with a valid endpoint token

1

Open the config file

Create or edit .mcp.json in your project root for project-level scope, or ~/.claude.json for user-level scope.
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

Restart Claude Code

Start a new Claude Code session. Type /mcp to confirm the server is connected. The tools will be automatically available in your conversation.

.mcp.json

{
  "mcpServers": {
    "helicone-llm-observability-mcp": {
      "type": "url",
      "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 Code

Run claude mcp add --transport http helicone-mcp -- . Make sure you put the transport flags before the server name. Verify the installation with claude mcp list.

Yes. You can run headless commands in a cron job to fetch daily cost summaries and push them to your monitoring stack.

The server provides full access to latency, costs, prompt logs, and user feedback. Your CLI agent reads this data to debug production LLM pipelines.

The agent uses `get_prompt_versions` to irreversibly vaporize explicit validations extracting rich churn flags. It prints the version history directly to your standard output.

The server handles explicit cloud logging and billing rules via the `query_sessions` endpoint. Vinkius strictly enforces stateless, zero-trust execution. Your terminal authenticates via a single endpoint token, leaving no persistent credentials exposed in your shell history.

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