Guance Cloud / 观测云 Connector for AI agents.
10 live capabilities
Manage cloud observability and incident response through natural language.
Waiting for input…
Why people use Guance Cloud / 观测云
Guance Cloud for Faster Incident Response
With this Connector, you just tell your agent what's wrong. It uses list_events to show you the latest alerts and query_data to pull the exact logs you need. You get the answer in seconds without ever leaving your chat interface.
What Vinkius changes
You get a conversational interface for your entire observability stack.
Use it from Claude, ChatGPT, Cursor or another AI client you already have.
One account · 5,900+ Connectors
- Real-world use case 01
Rapid Incident Response
An SRE notices a spike in latency and asks the agent to list_events and query_data to find the root cause in the logs.
- Real-world use case 02
Security Auditing
An infrastructure lead asks the agent to list_access_keys to ensure only authorized users have access to the workspace.
- Real-world use case 03
Cost Monitoring
A manager asks the agent for get_billing to see how much the production cluster spent over the last month.
Complete set · 10capabilities
The complete Guance Cloud / 观测云 capability set.
These are the exact actions your AI can choose when you ask it to work with Guance Cloud / 观测云.
01—04
4 capabilities in this set.
Part of 10 available through Guance Cloud / 观测云.
- 01 Capability
Get event
Pull specific details for a single system event. This helps you drill down into a specific alert or error.
- 02 Capability
Get monitor
Fetch the full configuration for a specific monitor. Use this to see exactly what triggers an alert.
- 03 Capability
Get workspace
Grab metadata and status for your Guance Cloud workspace. This provides context for your entire environment.
- 04 Capability
List access keys
View all API keys associated with your workspace. This is useful for security audits and permission management.
05—07
3 capabilities in this set.
Part of 10 available through Guance Cloud / 观测云.
- 05 Capability
List dashboards
See a full list of all dashboards in your account. Use this to get an overview of your monitoring layout.
- 06 Capability
List events
Browse a list of recent alerts, errors, and system changes. This is your first stop during an incident.
- 07 Capability
List log sources
See all the different log sources your system is tracking. Use this to verify your data ingestion.
08—10
3 capabilities in this set.
Part of 10 available through Guance Cloud / 观测云.
- 08 Capability
Query data
Execute DQL statements to get specific metrics or logs. Use this to run complex data lookups via natural language.
- 09 Capability
Get billing
Check your current spending and usage costs. Use this to stay on top of your infrastructure budget.
- 10 Capability
List monitors
Get a list of every monitor currently active in your workspace. Use this to see your overall system health.
Set up in minutes
One URL. Then ask Guance Cloud / 观测云 to work.
Claude and ChatGPT only need the Connector URL. Copy it once, add it in settings, and use Guance Cloud / 观测云 from the conversation.
Choose your client
Live previewAdvanced clients IDE · CLI
Claude · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_AANzdKMqG2pZyVDyBezhkEvdo4gPXGC9YiQz8RcU/mcp - Step 01
Open Connectors
In Claude Web or Claude Desktop, open Settings and choose Connectors.
- Step 02
Add the URL
Choose Add custom connector, name it Guance Cloud / 观测云, and paste the URL above.
- Step 03
Turn it on in chat
Select +, open Connectors, and enable Guance Cloud / 观测云 for the conversation.
ChatGPT · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_AANzdKMqG2pZyVDyBezhkEvdo4gPXGC9YiQz8RcU/mcp - Step 01
Open MCP settings
On desktop, open Settings and MCP servers. On web, open your workspace app or connector settings.
- Step 02
Add the URL
Choose Add server with Streamable HTTP, or create a custom MCP app, then paste the Guance Cloud / 观测云 URL.
- Step 03
Save and start
Save the connection and enable Guance Cloud / 观测云 in your conversation. Desktop may ask you to restart once.
Cursor · IDE configuration
Advanced setup
{
"mcpServers": {
"guance-cloud": {
"url": "https://edge.vinkius.com/vk_preview_AANzdKMqG2pZyVDyBezhkEvdo4gPXGC9YiQz8RcU/mcp"
}
}
}- Step 01
Open MCP Settings
Press Cmd+Shift+P (macOS) or Ctrl+Shift+P (Windows/Linux) → search "MCP Settings"
- Step 02
Add the server config
Paste the JSON configuration above into the mcp.json file that opens
- Step 03
Save the file
Cursor will automatically detect the new Connector
- Step 04
Start using Guance Cloud / 观测云
Open Agent mode in chat and ask: "Using Guance Cloud / 观测云, help me...". 10 tools available
VS Code Copilot · IDE configuration
Advanced setup
{
"mcpServers": {
"guance-cloud": {
"url": "https://edge.vinkius.com/vk_preview_AANzdKMqG2pZyVDyBezhkEvdo4gPXGC9YiQz8RcU/mcp"
}
}
}- Step 01
Create MCP config
Create a .vscode/mcp.json file in your project root
- Step 02
Add the server config
Paste the JSON configuration above
- Step 03
Enable Agent mode
Open GitHub Copilot Chat and switch to Agent mode using the dropdown
- Step 04
Start using Guance Cloud / 观测云
Ask Copilot: "Using Guance Cloud / 观测云, help me...". 10 tools available
Windsurf · IDE configuration
Advanced setup
{
"mcpServers": {
"guance-cloud": {
"url": "https://edge.vinkius.com/vk_preview_AANzdKMqG2pZyVDyBezhkEvdo4gPXGC9YiQz8RcU/mcp"
}
}
}- Step 01
Open MCP Settings
Go to Settings → MCP Configuration or press Cmd+Shift+P and search "MCP"
- Step 02
Add the server
Paste the JSON configuration above into mcp_config.json
- Step 03
Save and reload
Windsurf will detect the new server automatically
- Step 04
Start using Guance Cloud / 观测云
Open Cascade and ask: "Using Guance Cloud / 观测云, help me...". 10 tools available
Cline · IDE configuration
Advanced setup
{
"mcpServers": {
"guance-cloud": {
"url": "https://edge.vinkius.com/vk_preview_AANzdKMqG2pZyVDyBezhkEvdo4gPXGC9YiQz8RcU/mcp"
}
}
}- Step 01
Open Cline MCP Settings
Click the Connectors icon in the Cline sidebar panel
- Step 02
Add remote server
Click "Add Connector" and paste the configuration above
- Step 03
Enable the server
Toggle the server switch to ON
- Step 04
Start using Guance Cloud / 观测云
Ask Cline: "Using Guance Cloud / 观测云, help me...". 10 tools available
Claude Code · Terminal command
Advanced setup
claude mcp add guance-cloud --transport http "https://edge.vinkius.com/vk_preview_AANzdKMqG2pZyVDyBezhkEvdo4gPXGC9YiQz8RcU/mcp"- Step 01
Install Claude Code
Run npm install -g @anthropic-ai/claude-code if not already installed
- Step 02
Add the Connector
Run the command above in your terminal
- Step 03
Verify the connection
Run claude mcp to list connected servers, or type /mcp inside a session
- Step 04
Start using Guance Cloud / 观测云
Ask Claude: "Using Guance Cloud / 观测云, show me...". 10 tools are ready
Where the request belongs
Work Guance Cloud / 观测云 can move forward.
This is for the SRE or DevOps engineer who is tired of clicking through dozens of tabs during a high-pressure outage and needs instant answers from their logs.
SRE / DevOps Engineer
Uses this to troubleshoot production incidents by asking the agent to pull up specific error logs or monitor statuses.
Infrastructure Lead
Uses this to audit workspace configurations and API keys across the organization without manual exports.
Technical Analyst
Uses this to query specific metrics and log data for reports using natural language queries.
Build the capability set
Add more capabilities.
Each Connector adds new actions and data without changing how you work.
Browse ConnectorsDatadog
Monitor infrastructure, applications, and logs with unified observability that gives you full-stack visibility in real time.
Prometheus
Monitor your infrastructure with Prometheus. run PromQL queries, analyze metrics, and manage time-series data directly from your AI agent.
ncScale
Monitor and observe your no-code stack via ncScale. track logs, alerts, and tickets directly from your AI agent.
Tingyun / 听云
Leading APM and observability platform. manage applications, alerts, and performance metrics via AI.
SigNoz (Datadog Alternative)
Monitor infrastructure and manage alert rules via SigNoz. list, create, and update observability alerts directly from your AI agent.
Flystack
Manage cloud infrastructure. audit deployments, clusters, and metrics via AI.
Bring your own AI
Change the model, client or framework. Keep Guance Cloud / 观测云 connected.
-
Claude -
ChatGPT -
Gemini -
Cursor -
VS Code -
Windsurf -
ZCode -
Cline -
Zed -
Continue -
Kiro -
Roo Code -
Zencoder -
Goose -
Void -
Augment Code -
Amp -
Qodo -
Tabnine -
Pieces -
Sourcegraph Cody -
JetBrains -
Warp -
Amazon Q -
Antigravity -
BoltAI -
Raycast -
Jan -
LM Studio -
AnythingLLM -
Open WebUI -
Msty -
Cherry Studio -
LibreChat -
TypingMind -
Chorus -
5ire -
n8n -
LangChain -
LlamaIndex -
CrewAI -
Vercel AI SDK
Before you connect
Questions about Guance Cloud / 观测云.
The practical details behind the request, access and result.
Can Guance Cloud MCP help me with production outages?
Yes. It allows your agent to quickly pull alerts and logs so you can identify the root cause of an outage without manually searching through dashboards.
How do I use Guance Cloud MCP to query logs?
You can just ask your agent a question like 'Find the last 10 error logs for the login service.' The Connector will handle the data query for you.
Does Guance Cloud MCP support DQL?
Yes, it supports Data Query Language (DQL), allowing your agent to perform complex data lookups and metric retrievals on your behalf.
Can I check my billing with Guance Cloud MCP?
Absolutely. Your agent can check your current spending and usage costs instantly, helping you stay on top of your infrastructure budget.
How does Guance Cloud MCP help with security audits?
It makes auditing much faster by letting your agent list all workspace access keys and metadata, so you can verify permissions in seconds.
Can I see my dashboard list using Guance Cloud MCP?
Yes, your agent can retrieve a full list of all dashboards in your workspace to give you a high-level overview of your monitoring setup.
How do I find my Guance Cloud API Key?
Log in to your Guance Cloud workspace, navigate to [Management] → [API Key Management], and generate a new key. Use the provided value as your DF-API-KEY.
What is DQL?
Data Query Language (DQL) is the query syntax used by Guance Cloud to retrieve metrics, logs, and other observability data. You can use the query_data capability to execute these statements.
Can I check my data usage via the agent?
Yes. Use the get_billing capability to retrieve current data usage and billing statistics for your workspace, helping you manage costs and resource allocation.
One connection away
Give your agent a direct line to Guance Cloud / 观测云.
Connect Guance Cloud / 观测云 once. Keep it beside 5,900+ managed Connectors when the next task needs more.
Explore every Connector No credit card required · Free tier available