Grafana MCP Server
About
An MCP server for the comprehensive discovery, editing, and testing of dashboards and folders in one or more Grafana clusters.
Explore
+ Dashboard Protection: When creating Grafana dashboards, the MCP server labels them to mark itself as the origin
+ Selective Modification: Only dashboards with required protection labels can be updated or deleted
+ Unrestricted Reading: No restrictions for reading dashboards, allowing enhancement of existing dashboards by copying them
+ Folder Restrictions: Configurable access control to specific folders and subfolders
+ Multi-Cluster Support: Manage dashboards across multiple Grafana instances
+ Comprehensive Search: Full support for Grafana's search API with filtering options
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
Grafana MCP ServerCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
uv sync
python main.py
Configure the MCP server using these environment variables:
export GRAFANA_TOKENS="dev=glsa_yyy prod=glsa_zzz" # Note: localhost has no token (unauthenticated)
For local development, you can run Grafana in a Docker container without authentication:
docker run -d \
-p 3000:3000 \
-e "GF_AUTH_ANONYMOUS_ENABLED=true" \
-e "GF_AUTH_ANONYMOUS_ORG_ROLE=Admin" \
-e "GF_AUTH_BASIC_ENABLED=false" \
--name grafana \
grafana/grafana:latest
export GRAFANA_CLUSTERS="localhost=http://localhost:3000"
You can mix authenticated and unauthenticated clusters:
For production or authenticated Grafana clusters, you need to create service account tokens. Service accounts are the recommended way to authenticate with Grafana's HTTP API (API keys are deprecated).
Note: Skip this section if you're only using local unauthenticated Grafana instances.
The MCP server automatically adds the Bearer token to all requests:
Authorization: Bearer glsa_abc123def456
For more information, see the official Grafana documentation on service accounts.
1. Install dependencies:
uv sync
clusters = list_clusters()
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"grafana mcp server": {
"grafana": {
"command": "uv",
"args": [
"--directory",
"/ABSOLUTE/PATH/TO/grafana-mcp",
"run",
"main.py"
],
"env": {
"GRAFANA_CLUSTERS": "local=http://localhost:3000 dev=https://dev.example.com/grafana",
"GRAFANA_TOKENS": "dev=glsa_abc123xyz"
}
}
}
}
}McpServers
{
"grafana": {
"command": "uv",
"args": [
"--directory",
"/ABSOLUTE/PATH/TO/grafana-mcp",
"run",
"main.py"
],
"env": {
"GRAFANA_CLUSTERS": "local=http://localhost:3000 dev=https://dev.example.com/grafana",
"GRAFANA_TOKENS": "dev=glsa_abc123xyz"
}
}
}This repository provides an MCP (Model Context Protocol) server for the comprehensive discovery, editing, and testing
of dashboards and folders in one or more Grafana clusters.
Its security model is based on labels and folders.
Quick Start
```bash
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
