How to Use the Guance Cloud / 观测云 MCP in Google ADK

Q: Is Guance Cloud / 观测云 compatible with Google ADK long-context models?

Yes. Gemini models can process the large JSON outputs from querydata easily. This allows your agent to summarize extensive infrastructure logs without hitting token limits.

Q: Can I restrict which Guance Cloud / 观测云 tools Google ADK uses?

Absolutely. You use a toolnames filter to whitelist only the functions your agent needs. This limits the blast radius and keeps your agent focused on specific observability tasks.

Integrate Guance Cloud / 观测云 with Google ADK to power your enterprise agents with real-time infrastructure data.

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 Google ADK

Create your Vinkius account to connect Guance Cloud / 观测云 to Google ADK 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 Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Query metrics in Google ADK using MCP Server

Your agents can hit the `query_data` tool to pull specific performance metrics from your cloud environment. It processes DQL requests, allowing your Gemini-powered agents to reason over your infrastructure state. Use `list_log_sources` to map out exactly where your logs are flowing. This visibility ensures your agent always queries the right data source for the task at hand.

Manage workspace events in Google ADK

The `list_events` tool provides a clear feed of everything happening in your system. Your agent scans these events to correlate alerts with specific deployment timestamps. When you need to dig deeper, `get_monitor` provides the configuration state of your alerts. Your agent checks this to verify if a monitor is configured correctly or if it needs tuning.

Access workspace details via Google ADK tools

Call `get_workspace` to retrieve the current environment context. Your agent uses this to distinguish between staging and production environments automatically. Use `list_access_keys` to audit your security posture without leaving the terminal. It gives your agent the ability to report on key rotation status or permissions.

Setup guide

Set up Guance Cloud / 观测云 MCP in Google ADK

Prerequisites

Python 3.10+ installed
google-adk package (pip install google-adk)
Active Vinkius subscription with a valid endpoint token

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with Guance Cloud / 观测云 tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="Guance Cloud / 观测云_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Guance Cloud / 观测云 tools via MCP.",
    tools=mcp_tools,
)

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 Google ADK

It uses the McpToolset to expose server functions as native tools for your agent. This lets you call functions like `list_dashboards` just like any other Python method.

Yes. Gemini models can process the large JSON outputs from `query_data` easily. This allows your agent to summarize extensive infrastructure logs without hitting token limits.

Absolutely. You use a tool_names filter to whitelist only the functions your agent needs. This limits the blast radius and keeps your agent focused on specific observability tasks.

You manage access keys through the platform interface. The MCP Server respects the permissions attached to the key you provide during the initial connection.

The server operates in a V8-isolated sandbox with zero-trust architecture. Sensitive log data and event details are transmitted over encrypted channels only when your agent requests them.

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