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.

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` tool to execute these statements.

Can I check my data usage via the agent?

Yes. Use the `get_billing` tool to retrieve current data usage and billing statistics for your workspace, helping you manage costs and resource allocation.

Guance Cloud / 观测云 MCP Server for OpenAI Agents SDK 10 tools — connect in under 2 minutes

Name: Guance Cloud / 观测云
Availability: InStock
Author: Vinkius

openai.github.io/openai-agents-python/mcp

Built by Vinkius GDPR 10 Tools SDK

The OpenAI Agents SDK enables production-grade agent workflows in Python. Connect Guance Cloud / 观测云 through Vinkius and your agents gain typed, auto-discovered tools with built-in guardrails. no manual schema definitions required.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerStreamableHttp

async def main():
    # Your Vinkius token. get it at cloud.vinkius.com
    async with MCPServerStreamableHttp(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as mcp_server:

        agent = Agent(
            name="Guance Cloud / 观测云 Assistant",
            instructions=(
                "You help users interact with Guance Cloud / 观测云. "
                "You have access to 10 tools."
            ),
            mcp_servers=[mcp_server],
        )

        result = await Runner.run(
            agent, "List all available tools from Guance Cloud / 观测云"
        )
        print(result.final_output)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Guance Cloud / 观测云 MCP Server

Empower your AI agent to orchestrate your entire observability stack with Guance Cloud (观测云), the leading next-generation monitoring platform. By connecting Guance Cloud to your agent, you transform complex system monitoring, log analysis, and incident response into a natural conversation. Your agent can instantly list your monitors, retrieve detailed dashboard configurations, browse system events, and even execute Data Query Language (DQL) statements without you ever needing to navigate the Guance console. Whether you are troubleshooting a production outage or auditing resource usage, your agent acts as a real-time site reliability assistant, keeping your infrastructure data accurate and your systems healthy.

The OpenAI Agents SDK auto-discovers all 10 tools from Guance Cloud / 观测云 through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns. chain multiple agents where one queries Guance Cloud / 观测云, another analyzes results, and a third generates reports, all orchestrated through Vinkius.

What you can do

Workspace Orchestration — Retrieve detailed metadata and status information for your Guance Cloud workspace.
Monitoring Control — List and retrieve detailed configurations for all system monitors and alert rules.
Event Auditing — Browse real-time observability events, including alerts, errors, and system changes.
Data Querying — Execute powerful DQL statements to retrieve specific metrics and logging data via natural language.
Operations Insights — Monitor billing usage and manage API access keys for your organizational infrastructure.

The Guance Cloud / 观测云 MCP Server exposes 10 tools through the Vinkius. Connect it to OpenAI Agents SDK in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Guance Cloud / 观测云 to OpenAI Agents SDK via MCP

Follow these steps to integrate the Guance Cloud / 观测云 MCP Server with OpenAI Agents SDK.

Install the SDK

Run pip install openai-agents in your Python environment

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token from cloud.vinkius.com

Run the script

Save the code above and run it: python agent.py

Explore tools

The agent will automatically discover 10 tools from Guance Cloud / 观测云

Why Use OpenAI Agents SDK with the Guance Cloud / 观测云 MCP Server

OpenAI Agents SDK provides unique advantages when paired with Guance Cloud / 观测云 through the Model Context Protocol.

Native MCP integration via `MCPServerSse`, pass the URL and the SDK auto-discovers all tools with full type safety

Built-in guardrails, tracing, and handoff patterns let you build production-grade agents without reinventing safety infrastructure

Lightweight and composable: chain multiple agents and MCP servers in a single pipeline with minimal boilerplate

First-party OpenAI support ensures optimal compatibility with GPT models for tool calling and structured output

Guance Cloud / 观测云 + OpenAI Agents SDK Use Cases

Practical scenarios where OpenAI Agents SDK combined with the Guance Cloud / 观测云 MCP Server delivers measurable value.

Automated workflows: build agents that query Guance Cloud / 观测云, process the data, and trigger follow-up actions autonomously

Multi-agent orchestration: create specialist agents. one queries Guance Cloud / 观测云, another analyzes results, a third generates reports

Data enrichment pipelines: stream data through Guance Cloud / 观测云 tools and transform it with OpenAI models in a single async loop

Customer support bots: agents query Guance Cloud / 观测云 to resolve tickets, look up records, and update statuses without human intervention

Guance Cloud / 观测云 MCP Tools for OpenAI Agents SDK (10)

These 10 tools become available when you connect Guance Cloud / 观测云 to OpenAI Agents SDK via MCP:

get_billing

Get billing usage

get_event

Get event details

get_monitor

Get monitor details

get_workspace

Get workspace information

list_access_keys

List workspace access keys

list_dashboards

List all dashboards

list_events

) from the workspace. List observability events

list_log_sources

List log data sources

list_monitors

List all monitors

query_data

Query Guance data (DQL)

Example Prompts for Guance Cloud / 观测云 in OpenAI Agents SDK

Ready-to-use prompts you can give your OpenAI Agents SDK agent to start working with Guance Cloud / 观测云 immediately.

"List all active monitors in Guance Cloud."

"Show me recent events from the last hour."

"Query average CPU usage using DQL."

Troubleshooting Guance Cloud / 观测云 MCP Server with OpenAI Agents SDK

Common issues when connecting Guance Cloud / 观测云 to OpenAI Agents SDK through the Vinkius, and how to resolve them.

MCPServerStreamableHttp not found

Ensure you have the latest version: pip install --upgrade openai-agents

Agent not calling tools

Make sure your prompt explicitly references the task the tools can help with.

Guance Cloud / 观测云 + OpenAI Agents SDK FAQ

Common questions about integrating Guance Cloud / 观测云 MCP Server with OpenAI Agents SDK.

How does the OpenAI Agents SDK connect to MCP?

Use MCPServerSse(url=...) to create a server connection. The SDK auto-discovers all tools and makes them available to your agent with full type information.