How to Use the Guance Cloud / 观测云 MCP in Claude Code

Q: How do I run DQL queries using Claude Code and Guance Cloud / 观测云?

You ask Claude Code to query your metrics, and it executes querydata in the background. The terminal agent parses the DQL response and outputs the results directly to your shell.

Q: How does Claude Code handle Guance Cloud / 观测云 event investigation?

Claude Code uses listevents to retrieve active alerts and getevent to fetch specific details. This allows you to investigate production incidents completely from your terminal session.

Q: How do I install this MCP Server in my terminal environment?

Run claude mcp add --transport http -- to add the server to your configuration. You can verify the installation at any time by running claude mcp list.

Q: How are my workspace access keys secured when using this MCP Server?

Any access keys retrieved via listaccesskeys are kept strictly in-memory during your terminal session. Claude Code handles these credentials locally, ensuring your workspace security keys are never written to external logs or persistent remote storage.

Run DQL queries and audit alerts directly from your terminal using Claude Code and the Guance Cloud / 观测云 MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Guance Cloud / 观测云 MCP to Claude Code

Create your Vinkius account to connect Guance Cloud / 观测云 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 Guance Cloud / 观测云 with Claude Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Query telemetry data using Claude Code

The `query_data` tool lets Claude Code run raw DQL statements right from your shell, returning clean JSON payloads that you can instantly grep or pipe into other terminal utilities. This eliminates the need to open a web browser to check simple system statistics. You don't need to open a browser to check system metrics. This MCP Server lets you ask your terminal agent for the latest database latency or CPU spikes, and it will fetch the raw data and format the output for your terminal.

Triage active alerts via CLI commands

The `list_events` and `get_event` tools let Claude Code quickly pull critical system warnings and inspect the event payload to pinpoint which host is throwing errors. This speeds up your response times when on-call. Because Claude Code operates entirely in the terminal, it can correlate these alerts with your local system logs or git history. You get instant, context-aware triage commands without context switching.

Inspect workspace configuration and logs

The `list_log_sources` and `get_workspace` tools let Claude Code check which services are sending logs and verify workspace limits directly from the command line. This gives you a fast way to verify that your logging agents are configured correctly. This terminal-first approach lets you script your observability checks. You can run cron jobs or shell scripts that use Claude Code to monitor system health and alert your team via standard output.

Setup guide

Set up Guance Cloud / 观测云 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 guance-cloud-mcp with a green status indicator.
3

Start using tools

Ask Claude Code something like "Check my latest Guance Cloud / 观测云 transactions." It will automatically discover and invoke the available Guance Cloud / 观测云 tools.

Terminal

claude mcp add --transport http guance-cloud-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 Guance Cloud / 观测云 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": {
    "guance-cloud-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 Guance Cloud / 观测云. 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 Guance Cloud / 观测云 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 Guance Cloud / 观测云 MCP in Claude Code

You ask Claude Code to query your metrics, and it executes `query_data` in the background. The terminal agent parses the DQL response and outputs the results directly to your shell.

Yes, you can list all active monitors by telling Claude Code to run `list_monitors`. It will fetch the monitor configurations and display them in a clean terminal format.

Claude Code uses `list_events` to retrieve active alerts and `get_event` to fetch specific details. This allows you to investigate production incidents completely from your terminal session.

Run `claude mcp add --transport http -- ` to add the server to your configuration. You can verify the installation at any time by running `claude mcp list`.

Any access keys retrieved via `list_access_keys` are kept strictly in-memory during your terminal session. Claude Code handles these credentials locally, ensuring your workspace security keys are never written to external logs or persistent remote storage.

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