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

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

You ask Claude Desktop to query your data, and it uses the querydata tool to execute DQL statements. The results are returned directly in your chat, allowing you to analyze metrics without opening the web console.

Q: Can I manage active monitors in Guance Cloud / 观测云 from Claude Desktop?

Yes, you can inspect them. Claude Desktop calls listmonitors to show active alerts and getmonitor to drill down into specific configurations.

Q: Can I check billing usage through this setup?

Yes, you can run getbilling to see your current consumption. This helps you keep track of your observability costs directly from your chat interface.

Query metric databases and triage incidents directly in 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 Guance Cloud / 观测云 MCP to Claude Desktop

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Pull live observability data into Claude Desktop

The `query_data` tool pulls raw metrics, logs, and custom telemetry from your Guance workspace using DQL queries. Setting up this MCP Server lets you translate your plain English request into a precise DQL query, fetch the data, and present the results inside your Claude Desktop chat window. You can also run `list_log_sources` to check which telemetry pipelines are active before querying. This lets you inspect system health and verify log structures during debugging sessions.

Triage infrastructure alerts inside your chat

The `list_events` tool fetches active system alerts and operational failures directly into your workspace. When an incident occurs, tell Claude Desktop to pull the latest events to see what went wrong. Your agent can run `get_event` to drill down into the specific payload of any alert, revealing the root cause without context switching. To verify if a specific alert is a known issue, have the agent run `list_monitors` to pull the active rules. You get the exact configuration of the failing monitor via `get_monitor` so you can decide if the threshold needs to be tweaked.

Audit workspace settings and dashboards via MCP Server

The `list_dashboards` tool lists all configured monitoring views inside your Guance workspace. If you need to verify where a metric is displayed, Claude Desktop can scan this list to find the exact dashboard. You can also run `get_workspace` to check the status and metadata of your active environment. For security audits, the agent uses `list_access_keys` to inspect active credentials and `get_billing` to monitor usage costs. These tools give you complete operational visibility over your telemetry setup without having to click around the Guance UI.

Setup guide

Set up Guance Cloud / 观测云 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 Guance Cloud / 观测云 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 Guance Cloud / 观测云 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 guance-cloud-mcp.

json

{
  "mcpServers": {
    "guance-cloud-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 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 Desktop

You ask Claude Desktop to query your data, and it uses the `query_data` tool to execute DQL statements. The results are returned directly in your chat, allowing you to analyze metrics without opening the web console.

Yes, you can inspect them. Claude Desktop calls `list_monitors` to show active alerts and `get_monitor` to drill down into specific configurations.

It uses the API credentials you configure in your local config file. The MCP server handles the connection securely, passing requests from your local Claude Desktop client to the platform.

Yes, you can run `get_billing` to see your current consumption. This helps you keep track of your observability costs directly from your chat interface.

Your workspace access keys and event payloads remain local to your machine. The MCP server runs as a local subprocess, meaning your API tokens and raw logs are only sent directly to Guance endpoints and never stored on third-party servers.

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