4,500+ servers built on MCP Fusion
Vinkius
Grafana logo
Vinkius
Claude Desktop logo

How to Use the Grafana MCP in Claude

Query your telemetry and manage active alerts directly inside Claude Desktop for faster incident response.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

Grafana MCP on Cursor AI Code Editor MCP Client Grafana MCP on Claude Desktop App MCP Integration Grafana MCP on OpenAI Agents SDK MCP Compatible Grafana MCP on Visual Studio Code MCP Extension Client Grafana MCP on GitHub Copilot AI Agent MCP Integration Grafana MCP on Google Gemini AI MCP Integration Grafana MCP on Lovable AI Development MCP Client Grafana MCP on Mistral AI Agents MCP Compatible Grafana MCP on Amazon AWS Bedrock MCP Support
MCP Servers - Free for Subscribers
Claude Desktop

Connect Grafana MCP to Claude Desktop

Create your Vinkius account to connect Grafana to Claude Desktop 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

Monitor system health in Claude Desktop

Stop context switching between your monitoring stack and your chat window. Use `firing_alerts` to pull the current status of your production rules and see exactly what is broken right now. Your agent parses these alerts to identify which services require immediate attention. It gives you the raw data you need to start debugging without leaving the app.

Inspect dashboard logic with Claude Desktop

Find the right telemetry by running `search_dashboards` to locate specific panels by title or tag. Once you have the target, pass the UID to `get_dashboard` to see the underlying queries. This lets you verify if your observability setup is actually tracking the metrics you think it is. You get the full configuration JSON back, allowing your agent to cross-reference panel data against your current code.

Audit data sources in Claude Desktop

Check which databases are connected to your instance by calling `list_datasources`. This gives you a clear view of the available backends your monitoring setup relies on. Knowing your data source configuration prevents the agent from guessing where metrics originate. It ensures every query is directed at the correct storage engine for your specific environment.

Setup guide

Set up Grafana MCP in Claude Web or Desktop

  1. 1

    Open Claude Settings

    Go to claude.ai, click your profile icon, then navigate to Customize → Connectors.

  2. 2

    Add Custom Connector

    Click the "+" button and select Add custom connector. Paste your Vinkius endpoint URL: https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. For OAuth-protected servers, expand Advanced settings to add credentials.

  3. 3

    Start a conversation

    Open a new chat. The Grafana MCP tools are available immediately — no restart needed.

Endpoint URL

https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

No configuration file needed — paste the URL directly in the Claude web interface.

Available on Free (1 connector), Pro, Max, Team, and Enterprise plans.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

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 Claude Desktop

You call the `firing_alerts` tool within the chat interface. It returns a list of all currently triggered rules, including their labels and current state.
Yes, use the `search_dashboards` tool to find the UID based on a title or tag. You then feed that UID into `get_dashboard` to inspect the panel contents.
It does. Running `list_datasources` displays every configured backend connected to your Grafana instance, giving you a full map of your observability coverage.
Your MCP server handles all communication via an endpoint token. No raw credentials are ever exposed to the chat history, and the connection remains scoped to your specific instance.
This server only touches metadata related to alerts, dashboard configurations, and datasource connection strings. It never accesses your actual time-series metric values or logs.

Start using the Grafana MCP today

We host it, we monitor it, we maintain it. You just paste one token.

Built & Managed by Vinkius 30s setup 4 tools

We've already built the connector for Grafana. Just plug in your AI agents and start using Vinkius.

No hosting. No infrastructure. No complex setup.
All 4 tools are live and waiting. You're up and running in seconds.

Claude Claude
ChatGPT ChatGPT
Cursor Cursor
Gemini Gemini
Windsurf Windsurf
VS Code VS Code
JetBrains JetBrains
Vercel Vercel
+ other MCP clients

Vinkius gives your AI agents access to the full catalog of app connectors, all fully managed, secure, and enterprise-ready. One subscription, every tool you need.

Zero hosting required Full MCP catalog included Enterprise-grade security Auto-updated by Vinkius

Built, hosted, and secured by Vinkius. You just connect and go.