Monitoring and observability · MCP server
MCP grafana: MCP server, setup and security
MCP grafana is an open-source MCP server that lets an AI agent search dashboards, investigate incidents, and query data sources in Grafana. Its repository has 3,598 stars and its last commit is from October 23, 2026 and it is licensed under Apache-2.0.
| Adoption (stars) | 36/40 | |
|---|---|---|
| Maintenance | 30/30 | |
| Framework (licence, registry, official) | 30/30 |
What MCP grafana does
According to its repository: “Search dashboards, investigate incidents and query datasources in your Grafana instance.”
An MCP server gives an AI agent extra tools it calls during the conversation: the agent reads their description, decides to use them and gets the result back. MCP grafana is listed under Monitoring and observability, a category of 57 servers in the directory, where it ranks #4 by stars.
Installing and connecting MCP grafana
Distribution modes declared in the official MCP registry:
- Docker (OCI) image
- remote server (streamable-http): you connect to it by URL, with nothing to install locally
Like any MCP server, you declare it in your client's configuration (Claude Desktop, Claude Code, Cursor, VS Code, Codex…): a name, the command that starts it or its URL, and any environment variables. The client then starts it and lists its tools. Project language: Python.
The registry lists 2 secret variables to provide (API key, access token). Keep them in the client's environment variables, never in a shared file or a repository.
Security: what to check
An MCP server runs code with the rights you give it, and the model reads its tool descriptions: a malicious or compromised server can hijack the agent. Read the code, or pick a maintained and widely used server, before connecting it.
Points found for MCP grafana:
- Secrets: the server acts with your credentials. Create a dedicated key with minimum rights and an expiry date.
Good practice: grant only the rights needed (least privilege), require human approval for irreversible actions, and run the AI agent security check.
Project activity and maintenance
Created on December 24, 2024, the grafana/mcp-grafana repository has 3,598 stars and 475 forks, with 56 open issues. It has more stars than 96% of the servers in the directory. It received changes this month. Version published in the registry: v2.1.1 (October 20, 2026).
Stars measure attention, not quality: a recent, heavily promoted project can collect them fast, while a useful but niche server will have few.
Verdict
MCP grafana is one of the most solid servers in its category: followed, maintained and well framed.
Strengths
- Maintained by the service's own vendor
- Active project: recent commit
- Widely followed: 3.6K stars
- Listed in the official MCP registry
- Usable remotely, without installation
- Permissive licence (Apache-2.0)
Limitations
- Requires an API key or token
Avoid if…
- You do not want to give credentials to an agent
Alternatives
- Netdata81.1K ★
- Openstatus9.2K ★
- OneUptime7.8K ★
- Homebutler305 ★
- SolidPing26 ★
- Marmot Data Catalog623 ★
Learn more
Frequently asked questions
How do I install MCP grafana?
MCP grafana is distributed as Docker (OCI) image and a remote server. Add it to your client's MCP configuration (Claude Desktop, Cursor, VS Code…) following the README of grafana/mcp-grafana.
Is MCP grafana free?
The code is published under the Apache-2.0 licence and can be used free of charge. It needs an API key: the service it connects to may be paid.
Is MCP grafana safe?
Points to watch: secrets. Give it minimum rights and approve sensitive actions.
Is it an official server?
Yes: the awesome-mcp-servers list marks it as the service vendor's official implementation.
What are the alternatives to MCP grafana?
In the same category: Netdata, Openstatus, OneUptime, and Homebutler.
Related articles
- Build your own MCP server in 30 minutesOctober 24, 2026
- Automate your inbox with an AI agentOctober 18, 2026
- MCP, A2A, and tool calling: agent protocols explainedOctober 17, 2026
- Build an AI agent with n8n, without codingOctober 16, 2026
Neutrality. No affiliate links. No vendor pays to be reviewed, rated or ranked. Reviews are directed by François Chollet, neutral and factual, and every data point is dated and sourced. How we score