Full Supabase access: database, auth, storage, and edge functions.
Grafana
Query dashboards, Prometheus/Loki datasources, alerts, and incidents from an AI agent — official.
Quick answer
What it does
Exposes Grafana operations as MCP tools: dashboard search/edit, datasource queries (Prometheus, Loki, and 10+ others), alert-rule inspection, and Incident/OnCall/Sift workflows.
Best for
- Incident investigation across metrics + logs
- Querying Prometheus and Loki via one MCP
- Dashboard search and editing
- Alert-rule inspection
Not for
- Grafana versions before 9.0
- Direct datasource access without Grafana
Source: top-mcps.com/mcp/grafana — verified Oct 2026
Setup recipe
Pick your client, then follow the three steps.
- 1
Install
claude_desktop_config.jsonjson{ "mcpServers": { "grafana": { "command": "docker", "args": [ "run", "--rm", "-i", "-e", "GRAFANA_URL", "-e", "GRAFANA_SERVICE_ACCOUNT_TOKEN", "grafana/mcp-grafana", "-t", "stdio" ], "env": { "GRAFANA_URL": "${GRAFANA_URL}", "GRAFANA_SERVICE_ACCOUNT_TOKEN": "${GRAFANA_SERVICE_ACCOUNT_TOKEN}" } } } }Paste under mcpServers. Fully quit and reopen Claude after editing.
CLI or .mcp.jsonshell# export GRAFANA_URL=https://myinstance.grafana.net # export GRAFANA_SERVICE_ACCOUNT_TOKEN=glsa_your_token claude mcp add grafana -- docker run --rm -i -e GRAFANA_URL -e GRAFANA_SERVICE_ACCOUNT_TOKEN grafana/mcp-grafana -t stdioRun from your repo. Commit .mcp.json to share with your team.
.cursor/mcp.jsonjson{ "mcpServers": { "grafana": { "command": "docker", "args": [ "run", "--rm", "-i", "-e", "GRAFANA_URL", "-e", "GRAFANA_SERVICE_ACCOUNT_TOKEN", "grafana/mcp-grafana", "-t", "stdio" ], "env": { "GRAFANA_URL": "${GRAFANA_URL}", "GRAFANA_SERVICE_ACCOUNT_TOKEN": "${GRAFANA_SERVICE_ACCOUNT_TOKEN}" } } } }Global path: ~/.cursor/mcp.json. Reload window after editing.
.vscode/mcp.jsonjsonc{ "servers": { "grafana": { "command": "docker", "args": [ "run", "--rm", "-i", "-e", "GRAFANA_URL", "-e", "GRAFANA_SERVICE_ACCOUNT_TOKEN", "grafana/mcp-grafana", "-t", "stdio" ], "env": { "GRAFANA_URL": "${GRAFANA_URL}", "GRAFANA_SERVICE_ACCOUNT_TOKEN": "${GRAFANA_SERVICE_ACCOUNT_TOKEN}" } } } }VS Code uses the "servers" key (not "mcpServers").
~/.codeium/windsurf/mcp_config.jsonjson{ "mcpServers": { "grafana": { "command": "docker", "args": [ "run", "--rm", "-i", "-e", "GRAFANA_URL", "-e", "GRAFANA_SERVICE_ACCOUNT_TOKEN", "grafana/mcp-grafana", "-t", "stdio" ], "env": { "GRAFANA_URL": "${GRAFANA_URL}", "GRAFANA_SERVICE_ACCOUNT_TOKEN": "${GRAFANA_SERVICE_ACCOUNT_TOKEN}" } } } }Open via Cascade → hammer icon → Configure.
cline_mcp_settings.jsonjson{ "mcpServers": { "grafana": { "command": "docker", "args": [ "run", "--rm", "-i", "-e", "GRAFANA_URL", "-e", "GRAFANA_SERVICE_ACCOUNT_TOKEN", "grafana/mcp-grafana", "-t", "stdio" ], "env": { "GRAFANA_URL": "${GRAFANA_URL}", "GRAFANA_SERVICE_ACCOUNT_TOKEN": "${GRAFANA_SERVICE_ACCOUNT_TOKEN}" } } } }Open via the Cline sidebar → MCP Servers → Edit.
~/.continue/config.jsonjson{ "experimental": { "modelContextProtocolServers": [ { "transport": { "type": "stdio", "command": "docker", "args": [ "run", "--rm", "-i", "-e", "GRAFANA_URL", "-e", "GRAFANA_SERVICE_ACCOUNT_TOKEN", "grafana/mcp-grafana", "-t", "stdio" ], "env": { "GRAFANA_URL": "${GRAFANA_URL}", "GRAFANA_SERVICE_ACCOUNT_TOKEN": "${GRAFANA_SERVICE_ACCOUNT_TOKEN}" } } } ] } }Continue uses modelContextProtocolServers with a transport block.
~/.codex/config.tomlshell# ~/.codex/config.toml [mcp_servers.grafana] command = "docker" args = [ "run", "--rm", "-i", "-e", "GRAFANA_URL", "-e", "GRAFANA_SERVICE_ACCOUNT_TOKEN", "grafana/mcp-grafana", "-t", "stdio", ] env = { GRAFANA_URL = "${GRAFANA_URL}", GRAFANA_SERVICE_ACCOUNT_TOKEN = "${GRAFANA_SERVICE_ACCOUNT_TOKEN}" }Codex uses TOML. Each server is a [mcp_servers.<name>] subtable.
~/.config/zed/settings.jsonjsonc{ "context_servers": { "grafana": { "command": { "path": "docker", "args": [ "run", "--rm", "-i", "-e", "GRAFANA_URL", "-e", "GRAFANA_SERVICE_ACCOUNT_TOKEN", "grafana/mcp-grafana", "-t", "stdio" ] }, "env": { "GRAFANA_URL": "${GRAFANA_URL}", "GRAFANA_SERVICE_ACCOUNT_TOKEN": "${GRAFANA_SERVICE_ACCOUNT_TOKEN}" } } } }Zed calls them "context_servers". Settings live-reload on save.
ChatGPT → Apps directorynoneGrafana doesn't ship a hosted HTTPS endpoint today. ChatGPT supports remote MCP servers only — to use this server in ChatGPT you'll need to deploy it to a public HTTPS URL first (e.g. via Cloudflare Workers or Vercel) or wait for an official remote build.
- 2
Set required secrets
Set
GRAFANA_URL,GRAFANA_SERVICE_ACCOUNT_TOKENin your shell environment before launching your MCP client. - 3
Try a minimum working prompt
Minimum working prompt pending verification. Try any prompt from the MCP’s README once installed.
Tools & permissions
| Tool | Description | Args | Side effects |
|---|---|---|---|
search_dashboards | Search for dashboards. | — | Read |
get_dashboard_by_uid | Get a dashboard by uid. | — | Read |
update_dashboard | Update or create a dashboard. | — | Write |
list_datasources | List configured datasources. | — | Read |
query_prometheus | Execute a query against a Prometheus datasource. | — | Read |
query_loki_logs | Query and retrieve logs using LogQL. | — | Read |
list_incidents | List incidents in Grafana Incident. | — | Read |
create_incident | Create an incident in Grafana Incident. | — | Write |
list_oncall_schedules | List schedules from Grafana OnCall. | — | Read |
Security & scope
- Access scope
- Read + write
- Sandbox
- Authenticates with a Grafana service-account token, and the README documents the exact RBAC permission each tool requires (dashboards:read, datasources:query, alert.rules:read, …) plus the scope it can be limited to — so the token, not the server, decides what an agent can reach.
- Gotchas
- update_dashboard can overwrite an existing dashboard; grant dashboards:create/write only where agent edits are acceptable.
- Query tools run with datasources:query, which exposes whatever the underlying datasource can read — scope tokens to specific datasource UIDs rather than datasources:*.
Agent prompt pack
— copy into Claude, Cursor, or ChatGPT.Recommend the best MCP servers for [task: e.g. cloud & infrastructure work] in [client: Claude]. Constraints: - Prefer tools that are [official | open-source | read-only] — pick what matters for my use case. - Exclude MCPs that require [e.g. a paid plan, OAuth-only flows, remote-only transport]. - Return at most 3 picks, ranked. For each pick include: 1. One-sentence rationale. 2. The ready-to-paste install snippet for my client. 3. Any required secrets I need to create before installing. Cross-check the top-mcps.com listing: https://top-mcps.com/top-mcps-for-cloud-infrastructure
Compare Grafana MCP vs [AWS MCP] for the following job: [describe the job, e.g. "let an agent create GitHub issues on bug triage"]. Judge them on: - Setup time and complexity (what a new user hits first). - Auth model (none / API key / OAuth 2.1) and credential risk. - Transport (stdio / Streamable HTTP / SSE) and where the server runs. - Required secrets and the blast radius if they leak. - Operational risk in an unattended agent loop. - Which one is "good enough" for a weekend prototype vs. production. End with one sentence: which should I pick for my scenario, which is: [my scenario]. References: - https://top-mcps.com/mcp/grafana - top-mcps.com listing for AWS
Install the Grafana MCP server for my [client: Claude] at the default config path for that client. Use the exact install snippet published at https://top-mcps.com/mcp/grafana (fetch https://top-mcps.com/mcp/grafana.json for the canonical server.json if you can read URLs). Before finishing: 1. Create the required secrets (GRAFANA_URL, GRAFANA_SERVICE_ACCOUNT_TOKEN) and put them in the appropriate env block — do not hard-code them. 2. Restart or reload the client so it picks up the new server. 3. Verify the server is connected (green / running state) and at least one tool is listed. 4. If anything fails, read the client's MCP logs and report the exact error — do not silently retry. Confirm when done and list the tools the server now exposes.
Frequently asked questions
What changed
— 3 updates tracked.v0.17.2 released
v0.17.1 released
v0.17.0 released
More Cloud & Infrastructure MCPs
Other tools in the same category worth evaluating.
Manage payments, customers, and subscriptions through Stripe.
Reach the whole Cloudflare API from an agent — DNS records, Workers, R2, and the Registrar beta — through one hosted Code Mode server.
Compared with Grafana
Side-by-side breakdowns for the choices people most often weigh against this MCP.
Exploring Top MCPs for Cloud & Infrastructure? See all Cloud & Infrastructure MCPs →

