Grafana MCP Server

Official self-managed MCP server for Grafana observability, dashboards, alerts, and data queries.

Description

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.

Requirements

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

Installation instructions

What Grafana MCP Server is and why it matters

Grafana MCP Server is the official open-source MCP server from Grafana Labs for accessing Grafana instances, dashboards, data sources, alerts, and observability features. MCP means Model Context Protocol: a standard that lets an AI assistant do more than generate text by communicating with an external system through clearly defined tools. With a skill, the idea is related but the technical form is different: a skill is structured guidance, usually stored as SKILL.md, that tells Claude when a specific workflow applies, which steps to follow, and where the boundaries are. For users, the important point is not the buzzword but the practical effect: repeated work becomes a traceable workflow instead of being improvised from scratch every time.

The provider or official repository is the primary source here. Provider claims should be treated as such: according to the provider, certain tools, installation methods, or integrations are available; that does not replace verification in your own environment. MCP servers are especially important to evaluate carefully because a language model can gain access to operational systems through the server. Depending on the product, that access may be read-only or may include write operations. Skills are less about direct system permissions, but more about the quality and scope of the instructions the assistant follows. Both can be very useful in production, but both need conscious setup.

Step 1: Prerequisites

Before setup, clarify which environment will be used and which permissions are truly required. Local MCP servers usually need Node.js, Python, Docker, or another runtime tool, depending on the official instructions. Remote servers often require OAuth or an API key. OAuth means the user authorizes the application through the provider instead of manually copying a secret token into a configuration file. API keys are simpler, but riskier, because they must be treated like passwords.

For skills, you need a Claude environment that can load skills, either project-specific from a .claude/skills directory or user-specific from a personal skills folder. It is also important to understand that a skill only works well when the necessary context exists. A meeting skill without calendar or document access can still provide a useful structure, but it cannot magically retrieve information from systems that are not connected.

Step 2: Setup step by step

The safest starting point is always the official documentation or the official GitHub repository. First check how the project is installed, which environment variables are required, and whether there are several operating modes. Many MCP servers provide a local option via npx, uvx, or Docker and sometimes also a hosted option. Local operation is useful when internal services, local APIs, or private networks must be reached. Remote operation is more convenient when the provider offers OAuth and managed infrastructure.

After installation, the server or skill is added to the configuration of the chosen client. For MCP servers, that entry usually consists of a command, arguments, and environment variables, or an HTTP URL for a remote server. For skills, the SKILL.md file is placed into the correct directory or installed through a skills tool. Once configured, test with a small, harmless task to confirm that the assistant recognizes the server or skill correctly before allowing it to touch production data.

Security and best practices

The most important security principle is least privilege. A service account, API key, or OAuth grant should allow only the data and actions needed for the use case. If a product provides a read-only mode, tool profiles, or the ability to disable tool groups, start there. Write access to databases, dashboards, API collections, or production systems should only be enabled when there is a clear process for approval, logging, and recovery.

Secrets belong in environment variables or secret managers, not in chat messages, screenshots, or public repositories. For legal, financial, or personal data, also clarify which information is sent to the AI provider being used. A local MCP server does not automatically mean all data stays local; results may still be added to the context of a hosted model.

Practical example and limits

In practice, Grafana MCP Server is worthwhile when a team already works regularly with the underlying product and typical questions or steps repeat. An assistant can then find relevant information faster, add structure to preparation or analysis, and make routine work less error-prone. Limits appear when permissions are too broad, data sources are stale, or users treat the output as verified truth. The best use is therefore assistive: the agent accelerates research, preparation, and routine work, while expert decisions, approvals, and sensitive changes remain human-reviewed.

uvx mcp-grafana

Authentication

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

Required access permissions

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

Transmitted or stored data

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

Security risks

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

License and costs

License
Apache-2.0
Cost
free

The server is Apache-2.0 licensed. Costs depend on the Grafana installation used and provider terms.

Alternatives

Not recorded yet.

At a glance

Provider
Grafana
Status
Official server
Deployment
Local and remote
Current version
1.3.0
GitHub stars
3,670
Last reviewed
07.09.2026

Repository and documentation

Categories

Supported clients

Related guides

Guides and background related to this entry.

No related guides yet.