How to Use the HyperDX (Open Source Observability) MCP in Claude Code

Q: How do I search logs using Claude Code and HyperDX (Open Source Observability)?

You ask the CLI to search your logs. It executes listlogs with your specified filters and prints the matching telemetry directly in your terminal.

Q: Can I automate alert creation with HyperDX (Open Source Observability) in Claude Code?

Yes. You can script Claude Code to run createalert and deletealert as part of your terminal-driven deployment workflows.

Q: How does Claude Code fetch dashboard metrics from HyperDX (Open Source Observability)?

The CLI tool executes listdashboards to list your views, then uses getdashboard to retrieve specific panel configurations directly into your terminal session.

Drive HyperDX log searches and alert updates from your terminal using Claude Code's headless execution.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect HyperDX (Open Source Observability) MCP to Claude Code

Create your Vinkius account to connect HyperDX (Open Source 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 HyperDX (Open Source Observability) with Claude Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Headless Log Analysis and Event Triage

Run terminal-based diagnostics during high-pressure incidents. Claude Code uses `list_logs` and `list_events` to query your infrastructure telemetry directly from your shell, piping the output to other CLI tools. You don't need to click through a heavy web interface while your site is down. Just tell the CLI to find errors in your auth service, and it will pull the exact log lines you need.

Scriptable Alerting via MCP Server

Automate your monitoring configurations through your CI/CD pipelines. This MCP Server lets Claude Code execute `create_alert` and `delete_alert` dynamically during deployment scripts or cron jobs. You can script your deployments to automatically tear down old alerts with `delete_alert` and stand up fresh ones with `create_alert`. This keeps your alerting footprint minimal and precise.

Rapid Dashboard Metadata Inspections

Get quick status updates on your infrastructure without leaving your terminal session. Claude Code runs `list_dashboards` to pull your monitoring views and `get_dashboard` to check specific panel configurations. This gives your terminal agent the exact structural context of your production metrics. It can quickly verify if a dashboard is tracking the correct metrics after a major release.

Setup guide

Set up HyperDX (Open Source 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 hyperdx-open-source-observability-mcp with a green status indicator.
3

Start using tools

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

Terminal

claude mcp add --transport http hyperdx-open-source-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 HyperDX (Open Source 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": {
    "hyperdx-open-source-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 HyperDX. 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 HyperDX (Open Source 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 HyperDX (Open Source Observability) MCP in Claude Code

You ask the CLI to search your logs. It executes `list_logs` with your specified filters and prints the matching telemetry directly in your terminal.

Yes. You can script Claude Code to run `create_alert` and `delete_alert` as part of your terminal-driven deployment workflows.

The CLI tool executes `list_dashboards` to list your views, then uses `get_dashboard` to retrieve specific panel configurations directly into your terminal session.

It supports stdio, HTTP, and SSE transports. You can add it using the standard CLI command to register the MCP integration.

Your credentials reside in your local configuration file. The server processes your telemetry queries, log data, and alert rules in a secure, isolated sandbox, ensuring your private payloads are never 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