How to Use the Grafana MCP in Google ADK

Run enterprise-scale observability lookups by connecting your Google ADK pipelines to Grafana.

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 Google ADK

Create your Vinkius account to connect Grafana 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 Grafana with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Analyze Grafana telemetry with Google ADK

Gemini's massive context window lets your Google ADK agent ingest entire Grafana dashboard configurations. This MCP Server lets the agent run `get_dashboard` to pull highly complex panel configurations and queries. It feeds this deep Grafana configuration directly into the Google ADK model alongside your BigQuery logs. This allows the Gemini model to correlate live Grafana configurations with historical cloud database trends.

Execute automated SRE loops using this MCP Server

Your Google ADK agent runs continuous Grafana infrastructure checks. It calls `firing_alerts` to pull active alerts from your Grafana alerting system. The Google ADK agent parses the Grafana alert labels to identify the root cause. Because it integrates with Vertex AI, it can trigger automated mitigation scripts in your Google Cloud environment.

Discover Grafana data sources across your cloud

Multi-cloud environments often have dozens of isolated databases connected to Grafana. Your Google ADK agent calls `list_datasources` to see exactly where your metrics are stored. It uses `search_dashboards` to locate the correct Grafana dashboard UID before inspecting queries. This ensures your Google ADK agent is always looking at the correct telemetry source.

Setup guide

Set up Grafana 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 Grafana 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="Grafana_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Grafana 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 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 Google ADK

Use the McpToolset class with your Vinkius HTTP URL. Pass this toolset directly into your LlmAgent constructor to expose these MCP tools to Gemini.

Yes, you can pass an optional tool name filter to your toolset. This lets you restrict access to `firing_alerts` while hiding sensitive datasource configurations if needed.

This toolset supports both execution modes. For cloud-deployed agents, the streamable HTTP transport is the most reliable way to connect to your Vinkius endpoint.

Gemini's million-token context easily handles the raw output from `get_dashboard`. The model reads the entire panel layout to diagnose query bottlenecks.

All Grafana alert payload metadata and datasource credentials are processed within ephemeral, zero-trust V8 isolates. Your API keys are injected via environment variables and never exposed to the LLM.

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