# Grafana MCP server
> Search dashboards, run Prometheus and Loki queries, and work with alerts and incidents in Grafana Cloud or self-hosted Grafana.
- Listing: https://mcp.tc/i/grafana
- Connect: use the server's own URL `https://mcp.grafana.com/mcp` (OAuth sign-in at the server); clients connect to it directly. The listing link is a page, not an MCP endpoint.
- Type: remote (Streamable HTTP)
- Auth: OAuth sign-in
- Category: [Observability & Incidents](https://mcp.tc/c/observability)
- Vendor: Grafana Labs
- Verified: yes, mcp.tc checked that this is the official server (https://mcp.tc/verify). It says who runs the server, not that it is safe.
- Homepage:
- Repository:
- Package: oci `docker.io/grafana/mcp-grafana`
## About
Connects an assistant to a Grafana instance and the data sources behind it. It can search and read dashboards, create or patch them, list data sources, and run PromQL and LogQL queries against Prometheus and Loki. Optional tool groups cover SQL data sources, CloudWatch, InfluxDB and Google Cloud Logging.
A hosted endpoint at mcp.grafana.com uses OAuth sign-in, with the X-Grafana-URL header pointing at your Grafana Cloud instance. For self-hosted Grafana 9.0 or later, run the open source mcp-grafana package with uvx or Docker and set GRAFANA\_URL and GRAFANA\_SERVICE\_ACCOUNT\_TOKEN.
## What it can do
- Search dashboards by title, folder, tag or starred status
- Read dashboard summaries or specific properties with JSONPath
- Create, update or patch dashboards
- List configured data sources and their details
- Run PromQL queries and read Prometheus metadata
- Run LogQL log and metric queries against Loki
- Query SQL, CloudWatch and InfluxDB sources when enabled
## Example prompts
- "Find the dashboards tagged kubernetes in Grafana"
- "Run a PromQL query for the p95 request latency over the last hour"
- "Show error logs from Loki for the checkout service in the last 30 minutes"
- "Summarize the panels and variables on my API overview dashboard"
## Install
### Claude Code
1. Run this in a terminal, in your project folder:
```bash
claude mcp add --transport http grafana https://mcp.grafana.com/mcp
```
2. Start Claude Code, type `/mcp`, pick **grafana** and choose **Authenticate**. A browser window opens for the Grafana Labs sign-in.
Add `--scope user` to make it available in every project, not just this one.
### Claude Desktop
1. Open **Settings → Connectors** and click **Add custom connector**.
2. Name it **Grafana** and paste this URL:
```url
https://mcp.grafana.com/mcp
```
3. Click **Add**, then **Connect**, and sign in when Grafana Labs asks.
Claude Desktop’s JSON config file only starts local servers. Remote servers go through Connectors, and connectors you add on claude.ai show up here too.
### claude.ai
1. Open the connector form on claude.ai. This button fills in the name and URL for you:
[Add to claude.ai]() (opens connector settings)
2. Check that the URL reads `https://mcp.grafana.com/mcp` and click **Add**.
3. Click **Connect** and sign in when Grafana Labs asks.
Free plans allow one custom connector. On Team and Enterprise plans an owner adds it under **Organization settings → Connectors**.
### ChatGPT
1. On chatgpt.com, open **Settings → Security and login** and turn on **Developer mode**.
2. Go to `chatgpt.com/plugins` and click **+** to create an app for a remote MCP server.
3. Paste `https://mcp.grafana.com/mcp` as the server URL and choose **OAuth**. ChatGPT sends you to Grafana Labs to sign in.
Developer mode is available on the web for Plus, Pro, Business, Enterprise and Education accounts.
### Cursor
[Add to Cursor]() (opens Cursor)
Or add it by hand to `~/.cursor/mcp.json` (all projects) or `.cursor/mcp.json` (this project):
`mcp.json`:
```json
{
"mcpServers": {
"grafana": {
"url": "https://mcp.grafana.com/mcp"
}
}
}
```
Cursor shows **Needs login** next to the server. Click it to sign in.
### VS Code
[Install in VS Code]() (opens VS Code)
Or from a terminal:
```bash
code --add-mcp '{"name":"grafana","type":"http","url":"https://mcp.grafana.com/mcp"}'
```
Or commit it to the repo in `.vscode/mcp.json`:
`.vscode/mcp.json`:
```json
{
"servers": {
"grafana": {
"type": "http",
"url": "https://mcp.grafana.com/mcp"
}
}
}
```
VS Code asks you to sign in the first time the server starts.
### Devin Desktop
1. Add it to `~/.config/devin/mcp_config.json` (macOS and Linux) or `%APPDATA%\devin\mcp_config.json` (Windows):
`mcp_config.json`:
```json
{
"mcpServers": {
"grafana": {
"serverUrl": "https://mcp.grafana.com/mcp"
}
}
}
```
2. Refresh the MCP server list in Cascade and sign in when asked.
Devin Desktop is the new name for Windsurf. It reads `serverUrl` (or `url`) for remote servers.
### Codex
```bash
codex mcp add grafana --url https://mcp.grafana.com/mcp
codex mcp login grafana
```
Or edit `~/.codex/config.toml` directly:
`config.toml`:
```toml
[mcp_servers.grafana]
url = "https://mcp.grafana.com/mcp"
```
### Gemini CLI
```bash
gemini mcp add --transport http grafana https://mcp.grafana.com/mcp
```
Then, inside Gemini CLI, run `/mcp auth grafana` to sign in.
This adds it to the current project. Add `-s user` to use it everywhere.
### Any client
Most clients accept this shape. Some name the URL field differently: `serverUrl` in Devin Desktop, `httpUrl` in Gemini CLI’s settings file.
```json
{
"mcpServers": {
"grafana": {
"type": "http",
"url": "https://mcp.grafana.com/mcp"
}
}
}
```
Zed puts servers under `context_servers` in its settings. Cline needs `"type": "streamableHttp"`, or it assumes SSE.
Client only starts local servers? Bridge it with `npx -y mcp-remote https://mcp.grafana.com/mcp`.
## Details
- Server version: v2.0.0
- Last checked: 2026-10-03 (reachable, asks for credentials)
- Listed: 2026-10-03
- Updated: 2026-10-03
---
Source: https://mcp.tc/i/grafana (mcp.tc is an independent directory, not affiliated with this server's publisher). Corrections: https://mcp.tc/report