How to Use the Grafana MCP in LlamaIndex

Q: Can I index Grafana dashboard JSON directly into a LlamaIndex vector store?

Yes. You use getdashboard to pull the raw configuration, and LlamaIndex chunks and embeds the metrics queries. This lets you search your monitoring setups using natural language.

Q: How does LlamaIndex handle real-time changes to Grafana alerts?

The agent calls firingalerts dynamically during query time rather than indexing them statically. This ensures your LlamaIndex RAG pipeline always operates on live, real-time alert states.

Q: Can a LlamaIndex agent automatically discover new Grafana data sources?

Yes, the agent can call listdatasources to check for newly added databases. It then updates its internal index to include the new telemetry endpoints for future queries.

Q: Do I need to pre-configure every dashboard UID in LlamaIndex?

No. The agent runs searchdashboards to find the correct dashboard based on the user's query, gets the UID, and then fetches the details using getdashboard on the fly.

Index your Grafana dashboards and alerts into LlamaIndex to query live system health without hallucinations.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Grafana MCP to LlamaIndex

Create your Vinkius account to connect Grafana 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 Grafana with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build a LlamaIndex RAG index of Grafana dashboards

This MCP Server lets your LlamaIndex agent ingest raw dashboard configurations. By calling `get_dashboard`, the agent pulls down panel JSON and indexes the underlying Grafana metrics queries directly into your vector store. This means your LlamaIndex RAG application can answer complex questions about how your infrastructure is monitored. You can query your knowledge base to find out which Grafana dashboards track database latency.

Contextualize active alerts with historical data

When `firing_alerts` returns active Grafana incidents, your LlamaIndex agent doesn't just read the raw text. It queries your indexed runbooks to find matching mitigation steps for those specific alert labels. By combining live Grafana alert data with your LlamaIndex documents, the agent provides grounded troubleshooting steps. You avoid hallucinations because the response is tied directly to live Grafana states.

Map data sources to your knowledge graph

Your LlamaIndex agent uses `list_datasources` to discover all configured Grafana telemetry backends. It maps these sources against dashboards found via `search_dashboards` to build an accurate index of your data flow. This mapping helps the LlamaIndex agent route user queries to the correct Grafana database. If a user asks about system load, the agent knows exactly which data source to query.

Setup guide

Set up Grafana 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 Grafana 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 Grafana tools.",
)
response = await agent.run("List recent Grafana 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 Grafana. 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 Grafana 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 Grafana MCP in LlamaIndex

Yes. You use `get_dashboard` to pull the raw configuration, and LlamaIndex chunks and embeds the metrics queries. This lets you search your monitoring setups using natural language.

The agent calls `firing_alerts` dynamically during query time rather than indexing them statically. This ensures your LlamaIndex RAG pipeline always operates on live, real-time alert states.

Yes, the agent can call `list_datasources` to check for newly added databases. It then updates its internal index to include the new telemetry endpoints for future queries.

No. The agent runs `search_dashboards` to find the correct dashboard based on the user's query, gets the UID, and then fetches the details using `get_dashboard` on the fly.

All Grafana credentials are encrypted and isolated in the Vinkius sandbox. Your alert payloads and dashboard JSON are processed in memory and passed straight to LlamaIndex, ensuring your telemetry data never leaks to external logs.

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