grafana-mcp
MCP server for Grafana enabling management of dashboards, datasources, alert rules, folders, and annotations via stdio.
README
grafana-mcp
MCP server for Grafana — manage dashboards, datasources, alert rules, folders, and annotations over stdio.
Installation
bunx @daanrongen/grafana-mcp
Tools (17 total)
| Domain | Tools | Coverage |
|---|---|---|
| Dashboards | list_dashboards, get_dashboard, create_dashboard, update_dashboard, delete_dashboard |
Full dashboard lifecycle |
| Datasources | list_datasources, get_datasource, create_datasource, delete_datasource |
Datasource management |
| Alerts | list_alert_rules, get_alert_rule, list_alert_instances |
Alert rules and firing Alertmanager instances |
| Folders | list_folders, create_folder, delete_folder |
Folder organisation |
| Annotations | list_annotations, create_annotation |
Dashboard and global annotations |
| Health | health_check |
Grafana instance status |
Configuration
| Variable | Required | Description |
|---|---|---|
GRAFANA_URL |
Yes | Grafana base URL (e.g. http://localhost:3000) |
GRAFANA_API_KEY |
Yes | Grafana service account token or API key |
Setup
Claude Desktop
Edit ~/Library/Application Support/Claude/claude_desktop_config.json:
{
"mcpServers": {
"grafana": {
"type": "stdio",
"command": "bunx",
"args": ["@daanrongen/grafana-mcp"],
"env": {
"GRAFANA_URL": "http://localhost:3000",
"GRAFANA_API_KEY": "your-service-account-token"
}
}
}
}
Claude Code CLI
claude mcp add grafana \
-e GRAFANA_URL=http://localhost:3000 \
-e GRAFANA_API_KEY=your-service-account-token \
-- bunx @daanrongen/grafana-mcp
Development
bun install
bun run dev # run with --watch
bun test # run test suite
bun run typecheck # type-check with tsc
bun run lint # biome lint
bun run format # biome format
bun run build # bundle to dist/main.js
Inspecting locally
Use the MCP Inspector to browse and call tools interactively against a real Grafana instance:
GRAFANA_URL=http://localhost:3000 \
GRAFANA_API_KEY=your-service-account-token \
bun run inspect
This opens the MCP Inspector UI in the browser, pointed at the locally built server.
Architecture
src/
├── config.ts # Effect Config — GRAFANA_URL, GRAFANA_API_KEY
├── main.ts # Entry point — ManagedRuntime + StdioServerTransport
├── domain/
│ ├── GrafanaClient.ts # Context.Tag service interface (port)
│ ├── errors.ts # GrafanaError, NotFoundError
│ ├── models.ts # Schema.Class models (Dashboard, Datasource, AlertRule, …)
│ ├── dashboards.test.ts # Domain tests using GrafanaClientTest
│ ├── datasources.test.ts # Domain tests using GrafanaClientTest
│ └── health.test.ts # Domain tests using GrafanaClientTest
├── infra/
│ ├── GrafanaClientLive.ts # Layer using fetch against the Grafana HTTP API
│ └── GrafanaClientTest.ts # In-memory Ref-based test adapter
└── mcp/
├── server.ts # McpServer wired to ManagedRuntime
├── utils.ts # formatSuccess, formatError
└── tools/ # dashboards.ts, datasources.ts, alerts.ts, folders.ts, annotations.ts, health.ts
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.