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

Q: Can I index Guance Cloud / 观测云 dashboards for semantic search in LlamaIndex?

Yes, the agent can call listdashboards to pull metadata about your active views. This metadata is then indexed so you can search for dashboards by topic or service name.

Q: How can I filter which MCP tools the LlamaIndex agent can access?

You can use the allowedtools filter during setup. This lets you restrict the agent to specific read-only tools like listmonitors while blocking access to sensitive keys.

Q: Where do my Guance Cloud access keys and workspace configurations go?

Your access keys retrieved via listaccesskeys are never cached or stored on disk. All operations run within an ephemeral sandbox, ensuring your authentication tokens remain private and secure during execution.

Index live Guance Cloud telemetry directly into your LlamaIndex vector store to eliminate agent hallucinations using 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 LlamaIndex

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build a dynamic RAG pipeline for system events

The system uses `list_events` to retrieve active alerts and ingest them directly into your index. Instead of relying on static runbooks, your LlamaIndex agent combines live event data with historical incident logs to find solutions. The agent runs `get_event` to pull deep details on a specific failure, then indexes the payload. When you query your knowledge base about recent outages, the agent retrieves the exact telemetry context, grounded in real-time facts.

Map MCP Server monitors to your vector store

This MCP Server lets your agent query your monitoring setup using `list_monitors`. The agent indexes these monitor configurations so you can ask natural language questions about what is currently being watched. You can ask which alerts are set up for a specific microservice. The agent queries `get_monitor` for details, matches them against your service architecture documents, and flags any gaps in your monitoring coverage.

Query historical telemetry using semantic search

The agent uses `query_data` to run DQL queries and feed the raw metrics into a vector index. This turns raw time-series data into a searchable knowledge base for your engineering team. Instead of writing complex query syntax yourself, you let the agent retrieve data, index it, and summarize trends. It makes analyzing system performance over the last month as simple as asking a question in Slack.

Setup guide

Set up Guance Cloud / 观测云 MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all Guance Cloud / 观测云 MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to Guance Cloud / 观测云 tools.",
)
response = await agent.run("List recent Guance Cloud / 观测云 data")

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 LlamaIndex

Install the llama-index-tools-mcp package and initialize the client. You can convert the server tools into a tool list and pass them to your FunctionAgent.

Yes, the agent can call `list_dashboards` to pull metadata about your active views. This metadata is then indexed so you can search for dashboards by topic or service name.

By grounding the agent's context in real data retrieved via `query_data`. The agent must use the tool output to construct its response, ensuring answers match actual system metrics.

You can use the allowed_tools filter during setup. This lets you restrict the agent to specific read-only tools like `list_monitors` while blocking access to sensitive keys.

Your access keys retrieved via `list_access_keys` are never cached or stored on disk. All operations run within an ephemeral sandbox, ensuring your authentication tokens remain private and secure during execution.

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