Grafana MCP Server

Grafana MCP Server is Grafana Labs’ official self-managed open-source MCP server. It connects MCP-capable AI clients to a Grafana instance and, depending on configuration, can expose dashboards, folders, datasources, alerts, incidents, OnCall information, SLOs, snapshots, metrics, and log queries. The direct product link points to Grafana’s official documentation, while the repository contains source code, releases, and license information. For Skill Road users, the server matters because observability data often sits exactly where a coding agent needs concrete operational context: which alerts are firing, which dashboards show anomalies, which logs match a reported issue, and what became visible in monitoring after a release or infrastructure change?

Official server for owned Grafana instances

According to Grafana Labs, the server runs locally or on owned infrastructure and can be deployed through uvx, Docker, a binary, or Helm. Full functionality requires Grafana 9.0 or later. Rather than being a hosted chatbot, it is a controlled bridge between an existing Grafana system and an agent such as Claude Code, Codex, or Cursor. The domain source remains the user’s Grafana instance; the AI client receives only the tools and permissions the operator grants. In practice, this makes it useful for DevOps, SRE, and development teams that do not want to jump manually between repository, ticket, terminal, and observability UI during incident triage or release follow-up.

Tools, permissions, and safe boundaries

The server acts with the permissions of the configured Grafana credential. The documentation recommends a service-account token; username and password are also supported. The important decision is to keep that access narrow. If an agent only needs to explain dashboards and alerts, it does not need administrative rights. For analysis-only use, --disable-write and --disable-query are important because they can deliberately turn off write operations or datasource queries. Without those boundaries, a broadly privileged token can expose sensitive monitoring data or change configuration. That makes least-privilege setup, token rotation, and auditability part of the implementation rather than optional cleanup.

Use in analysis and incident workflows

The value is not just a set of individual API calls, but the ability to combine observability context with code and incident data. An agent can compare a Sentry issue, a GitHub change, and a Grafana dashboard when all sources are connected under deliberate permissions. It can summarize alerts, locate dashboards, explain panel queries, or inspect logs for a specific time range. This does not replace a human incident commander or a reviewed postmortem, but it can shorten the first orientation phase. The server is especially useful where teams already rely on repeatable runbooks and Grafana is the central source for metrics and operational state.

License, version, and GitHub stars

The repository is Apache-2.0 licensed. The GitHub API reported exactly 3,423 stars on 2026-09-07; that snapshot is a popularity signal, not proof of security or quality. Version v1.3.0 was documented as the current release. The server itself is open source, but it is only useful with a suitable Grafana environment; costs therefore come from the organization’s Grafana deployment, provider plans, or infrastructure rather than from any fixed public price stated here. Before production use, teams should review token scope, logging, data classification, and the approved path from Grafana data into their selected AI client.

Grafana 9.0+, an MCP client, and a service-account token or user credentials.

Deploy through uvx, Docker, binary, or Helm; use a least-privilege service account and register the client.

uvx mcp-grafana

A Grafana service-account token is recommended; username and password are alternatives.

Tools act with the token’s RBAC permissions and may read or write depending on configuration.

Requests go to the configured Grafana API and results return to the connected AI client.

Broad RBAC permissions or enabled write and query tools can expose or change infrastructure information. Use --disable-write and --disable-query for analysis tasks.