mcp-read-only-grafana
MCP server for read-only access to Grafana instances
How to use
The mcp-read-only-grafana server provides a Model Context Protocol (MCP) interface for accessing Grafana instances in a read-only mode. This server allows developers to efficiently query and retrieve Grafana dashboards, panels, and other visualizations without modifying any data. It is particularly useful for integrating Grafana insights into applications or services where data integrity and security are paramount.
Once connected to the mcp-read-only-grafana server, you can interact with it using standard MCP queries to retrieve visual data from your Grafana instances. You can execute commands to fetch dashboards or specific panel data by specifying their IDs. It's best to use well-structured queries that align with the Grafana API to ensure you get the most relevant and accurate data.
How to install
Prerequisites
- Ensure you have Node.js installed on your machine. You can download it from nodejs.org.
Option A: Quick Start with npx
For a quick start, you can run the server using npx:
npx -y mcp-read-only-grafana
Option B: Global Install Alternative
Alternatively, you can install it globally if you prefer:
npm install -g mcp-read-only-grafana
Additional notes
For optimal performance, you may want to configure environment variables such as GRAFANA_URL to specify the Grafana instance you are accessing. Additionally, ensure that your Grafana instance is set up to allow read-only access to prevent unauthorized data modification. Common issues include misconfigured API keys or network restrictions that may block access to your Grafana server.
Related MCP Servers
mcp-pinecone
Model Context Protocol server to allow for reading and writing from Pinecone. Rudimentary RAG
Gitingest
mcp server for gitingest
mcp-victoriametrics
The implementation of Model Context Protocol (MCP) server for VictoriaMetrics
microsoft_fabric_mcp
MCP server wrapping around the Fabric Rest API
mcp -memos-py
A Python package enabling LLM models to interact with the Memos server via the MCP interface for searching, creating, retrieving, and managing memos.
mcp -python-template
This template provides a streamlined foundation for building Model Context Protocol (MCP) servers in Python. It's designed to make AI-assisted development of MCP tools easier and more efficient.