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

Q: How does Windsurf use the Guance Cloud / 观测云 MCP integration to debug active incidents?

Windsurf uses Cascade to autonomously run querydata and listevents when an alert is detected. It chains these tools to locate the failing service and display the raw logs right inside your editor.

Q: Can I manage my Guance Cloud / 观测云 dashboards directly from Windsurf?

Yes. Cascade can call listdashboards to check your current visualization setup and map it against active workspace metrics. This lets you inspect your telemetry layout without leaving your coding session.

Q: Does this Guance Cloud / 观测云 MCP Server support custom DQL queries in Windsurf?

Yes, Cascade invokes querydata to execute arbitrary DQL queries directly. It parses the returned dataset to help you write code that targets specific infrastructure performance bottlenecks.

Q: How do I configure this MCP Server in my editor?

Add the server configuration to your /.codeium/windsurf/mcpconfig.json file under the mcpServers key. Once saved, Cascade immediately discovers the tools and can begin querying your workspace.

Q: How does this integration handle my Guance workspace credentials and access keys?

Your workspace access keys retrieved via listaccesskeys and raw telemetry logs are processed locally within the Windsurf environment. No API tokens or raw query results are sent to external third-party servers; everything stays inside your local sandbox.

Get live telemetry and incident alerts directly inside Windsurf as Cascade autonomously diagnoses infrastructure issues with this 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 Windsurf

Create your Vinkius account to connect Guance Cloud / 观测云 to Windsurf 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 Windsurf

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Auto-diagnose incidents with DQL queries

The `query_data` and `list_log_sources` tools let Cascade run raw DQL queries and pull related logs to isolate the exact microservice failure without you typing a single command. Cascade acts on live telemetry data immediately after an alert fires, bypassing manual log-diving entirely. By analyzing historical trends and mapping them against active workspace thresholds, your autonomous IDE agent correlates telemetry patterns to find the root cause. You get a complete diagnosis pipeline executed in a single turn without leaving your code editor.

Map active workspaces and monitors

The `get_workspace` and `list_monitors` tools let Cascade navigate your observability setup to build a mental map of your production health. If a threshold looks wrong, the agent inspects the monitor logic with `get_monitor` to find misconfigured alert conditions. Instead of jumping back and forth to your browser, you let Windsurf audit your alert coverage. The IDE reads the active monitor states, compares them against live events, and suggests immediate fixes to your alerting rules.

Track event cascades with this MCP Server

The `list_events` and `get_event` tools let Cascade pull the full incident trail and inspect specific failures to trace how a database lag triggered an API timeout. This keeps your debugging process focused on chronological facts rather than guesswork. Cascade uses these tools to build a chronological timeline of your system failures. You watch the IDE parse the event payloads, isolate the initial breaker, and point you directly to the offending line of code in your workspace.

Setup guide

Set up Guance Cloud / 观测云 MCP in Windsurf

Prerequisites

Windsurf IDE installed (macOS, Windows, or Linux)
Active Vinkius subscription with a valid endpoint token

1

Open MCP configuration

Click the Cascade assistant icon in the sidebar, then click the hammer icon (🔨) at the top of the panel. Select "Configure" to open ~/.codeium/windsurf/mcp_config.json.
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

Refresh MCPs

Go back to the hammer icon (🔨) in Cascade and click "Refresh". Windsurf will detect the new server. No full restart is needed — the connection is hot-reloaded.
4

Verify in Cascade

Start a new Cascade conversation and ask something like "Show my Guance Cloud / 观测云 payment history." If connected, Cascade will call the Guance Cloud / 观测云 tools directly. You will see a green dot next to the server name in the MCP panel.

mcp_config.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 Windsurf

Windsurf uses Cascade to autonomously run `query_data` and `list_events` when an alert is detected. It chains these tools to locate the failing service and display the raw logs right inside your editor.

Yes. Cascade can call `list_dashboards` to check your current visualization setup and map it against active workspace metrics. This lets you inspect your telemetry layout without leaving your coding session.

Yes, Cascade invokes `query_data` to execute arbitrary DQL queries directly. It parses the returned dataset to help you write code that targets specific infrastructure performance bottlenecks.

Add the server configuration to your `~/.codeium/windsurf/mcp_config.json` file under the `mcpServers` key. Once saved, Cascade immediately discovers the tools and can begin querying your workspace.

Your workspace access keys retrieved via `list_access_keys` and raw telemetry logs are processed locally within the Windsurf environment. No API tokens or raw query results are sent to external third-party servers; everything stays inside your local sandbox.

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