Grafana MCP Server — 50 AI Tools | Claude, ChatGPT & More

Grafana MCP ServerGrafana MCP server with 50 ready-to-use AI tools. Connect Grafana to Claude, ChatGPT, Gemini, or any MCP-compatible AI assistant. Cloud MCP connector — no install, no Docker, works from any browser.Category: Developer Tools. 50 tools available. Authentication: API Key.Build dashboards and query metrics by just describing what you needWhy Grafana + AI?Creating Grafana dashboards requires writing PromQL, configuring panels, and navigating a complex UI. Let AI build dashboards, write queries, and set up alerts for you through simple conversation.Example prompts you can send your AI about Grafana

Ask: "Create a dashboard showing CPU, memory, and disk usage for production servers"
AI does: AI creates a new dashboard with three panels, writes the correct PromQL queries, and organizes them in a clean layout.

Ask: "Set up an alert when API latency exceeds 500ms for 5 minutes"
AI does: AI creates an alert rule with the right threshold, evaluation interval, and notification contact point.

Ask: "Which datasources are configured and are they healthy?"
AI does: AI lists all datasources with their type, URL, and tests each one to report their health status.

Ask: "Add a panel to the Production dashboard showing request rate by endpoint"
AI does: AI adds a time series panel with a PromQL query broken down by endpoint, formatted with proper legends.

Featured Grafana Tools

grafana-create-dashboard: Create a new dashboard with full configuration. Supports time range, refresh interval, timezone, template variables, and panels with all visual options. STEP-BY-STEP: 1. grafana-list-datasources → get datasource UID. 2. grafana-list-datasource-metrics → find metrics. 3. grafana-query-datasource → test queries. 4. grafana-create-dashboard with title + panels array. WHEN TO USE: User asks "create a dashboard", "build a monitoring dashboard", "make a dashboard for X".

grafana-add-panel: Add a panel to an existing dashboard. Supports ALL 27 Grafana panel types: timeseries, stat, gauge, table, bargauge, piechart, heatmap, barchart, histogram, text, logs, row, state-timeline, status-history, xychart, candlestick, trend, geomap, nodeGraph, canvas, traces, flamegraph, dashlist, alertlist, annolist, news, datagrid. STEP-BY-STEP: 1. grafana-list-datasources → get UID. 2. grafana-query-datasource → test query. 3. grafana-add-panel with dashboardUid, type, title, datasourceUid, query. LAYOUT: Grid is 24 columns wide. Two side-by-side panels: x=0,width=12 and x=12,width=12. Full width: width=24. WHEN TO USE: User asks "add a panel", "add a chart for CPU", "put a stat widget on dashboard X".

grafana-query-datasource: Execute a query against a data source and return sample data. Returns a LIMITED sample (default: 10 rows, max 100) to avoid overwhelming context. EXAMPLES: PromQL instant: query="up". PromQL rate: query="rate(http_requests_total[5m])", from="now-1h". STEP-BY-STEP: 1. grafana-list-datasource-metrics to find metrics. 2. grafana-query-datasource with small maxRows to understand data shape. 3. Build dashboard panels from proven queries. WHEN TO USE: User asks "query Prometheus", "show me CPU data", "test this PromQL expression", "what does metric X look like?".

grafana-create-alert-rule: Create an alert rule. Evaluates a PromQL query against a condition and triggers notifications when breached. EXAMPLE: CPU alert: query="100 - (avg(rate(node_cpu_seconds_total{mode=\"idle\"}[5m])) * 100)", condition="gt 90", for="5m", labels={"severity":"critical"}. STEP-BY-STEP: 1. grafana-list-datasources → get UID. 2. grafana-list-folders → get folderUid. 3. grafana-create-alert-rule with name, query, condition. WHEN TO USE: User asks "create an alert", "alert me when CPU is above 90%", "set up monitoring alert".

grafana-list-dashboards: Search and list dashboards. Returns UID, title, folder, tags, and URL. Use filters to narrow by query text, tag, or folder. WHEN TO USE: User asks "show my dashboards", "find dashboard X", "list dashboards tagged production".

grafana-list-datasources: List all configured data sources. Returns UID, name, type (prometheus, influxdb, elasticsearch, etc.), URL, and access mode. CRITICAL: Call this FIRST before querying — you need a datasource UID for almost every other Grafana operation. WHEN TO USE: User asks "what data sources are available?", "show my datasources", or you need a UID to query/build dashboards.

Frequently Asked Questions about GrafanaCan my AI query Prometheus or Loki data via Grafana?Yes. The Grafana integration exposes datasource query tools — the AI can run PromQL against Prometheus or LogQL against Loki and interpret the results. You just need your Grafana API key with viewer permissions on the datasources you want exposed.Does the Grafana connector work with self-hosted Grafana?Yes, as long as your self-hosted Grafana is reachable from learntospeak.ai. We support both Grafana Cloud and self-hosted setups — enter your Grafana instance URL and API key in the dashboard. For air-gapped internal Grafana, you will need to whitelist our IP in your firewall.Can the AI create or modify Grafana dashboards?Yes. The integration includes 56 tools covering dashboards, panels, datasources, and alerts — including CRUD operations. Your AI can create a new dashboard, add panels with specific queries, and save it back to Grafana, all from a natural-language request.Is it safe to give an AI access to my Grafana alerts?Your Grafana API key is encrypted with AES-256-GCM and scoped to the permissions you grant when creating it. For read-only analysis, use a Viewer-role key. For alert modifications, use an Editor-role key. Revocation is instant — delete the key in Grafana or remove it from LearnToSpeak.ai.How do I connect Grafana to Claude or ChatGPT?Create a free LearnToSpeak.ai account, add your Grafana credentials in the dashboard, and paste the generated OAuth URL into Claude.ai's custom connectors or ChatGPT's developer apps. The integration runs fully in the cloud — no desktop app, no CLI, no local install.Does it cost anything to connect Grafana?The Grafana integration is free during the LearnToSpeak.ai public beta. You only need a paid plan from Anthropic or OpenAI (Claude Pro/Max/Team or ChatGPT Plus/Pro/Team) since custom connectors require it on the AI provider side.Which AI assistants support the Grafana connector?Claude.ai (Pro, Max, Team, Enterprise) and ChatGPT (Plus, Pro, Team) both support the Grafana integration via the MCP (Model Context Protocol) standard. The same credentials work across both platforms — add the connector once, use it everywhere.How many Grafana tools does my AI get access to?Your AI gets 50 ready-to-use tools for Grafana, covering the most common read and write operations. Each tool is a discrete action the AI can call on demand — no multi-step prompting, no screen scraping, no workarounds.Is it safe to give an AI access to my Grafana account?Yes. Your Grafana credentials are encrypted at rest with AES-256-GCM and only decrypted in memory when the AI makes a request. LearnToSpeak.ai uses OAuth 2.1 with mandatory PKCE for the AI-to-platform connection, and you can revoke access instantly from the dashboard. We never store or log the actual tool responses returned to the AI.Why use LearnToSpeak.ai instead of running an MCP server locally?Cloud MCP servers work from any browser on any device — no Node.js install, no Docker, no local ports, no maintenance. Configure Grafana once in the dashboard and your AI connects from claude.ai or chat.openai.com directly. That's the entire value proposition: web AI assistants don't read your filesystem, they read our servers.What is the Grafana MCP server?The Grafana MCP server is a cloud-hosted integration that gives AI assistants direct access to Grafana through 50 tools via the Model Context Protocol (MCP) standard. It works with Claude, ChatGPT, Gemini, and any MCP-compatible AI — no local installation or Docker required.How do I connect Grafana to Claude via MCP?Sign up at LearnToSpeak.ai, add your Grafana credentials, and copy the generated MCP URL into Claude.ai's custom connectors (Settings → Developer → Custom Connectors). The cloud MCP server handles the connection — no CLI, no local server, no Docker.How do I connect Grafana to ChatGPT via MCP?Sign up at LearnToSpeak.ai, add your Grafana credentials, and copy the generated MCP URL into ChatGPT's developer apps (Settings → Apps → Advanced → Developer mode). Works with any ChatGPT Plus, Pro, or Team account.What can AI do with Grafana through MCP?Grafana offers 50 MCP tools covering Query data, create dashboards, manage alerts and permissions in Grafana. Ask your AI to perform any of these actions in natural language — it calls the right tool automatically.What is MCP (Model Context Protocol)?MCP is an open standard that lets AI assistants like Claude, ChatGPT, and Gemini connect directly to external apps and services. LearnToSpeak.ai hosts cloud MCP servers so you don't need to install anything locally — your AI connects from any browser.Related MCP Servers

GitHub MCP Server — 44 tools

GitLab MCP Server — 90 tools

NetBox MCP Server — 179 tools

Cisco CPNR MCP Server — 36 tools

Graylog MCP Server — 12 tools

Browse all 34 MCP servers