mcp-grafana
Verified Safeby grafana
Overview
Provides an MCP interface to Grafana, enabling AI assistants to interact with dashboards, datasources, Prometheus, Loki, incidents, alerting, OnCall, Sift, Pyroscope, and admin functionalities for observability and automation.
Installation
docker run --rm -i -e GRAFANA_URL=$GRAFANA_URL -e GRAFANA_SERVICE_ACCOUNT_TOKEN=$GRAFANA_SERVICE_ACCOUNT_TOKEN mcp/grafana -t stdioEnvironment Variables
- GRAFANA_URL
- GRAFANA_SERVICE_ACCOUNT_TOKEN
- GRAFANA_USERNAME
- GRAFANA_PASSWORD
- GRAFANA_ORG_ID
Security Notes
The server correctly uses environment variables for sensitive credentials (API keys, passwords) and supports TLS configuration for both client (connecting to Grafana) and server (Streamable HTTP transport) connections. Access control is delegated to Grafana's RBAC system, requiring specific permissions for each tool, which is well-documented. The use of `gval` for JSONPath evaluation is a controlled query language, not arbitrary code execution. The `--tls-skip-verify` flag is explicitly marked as insecure and intended for development/testing purposes, not production use. No 'eval' or obvious malicious patterns were found in the provided source code.
Similar Servers
inspector
Inspect, debug, and interact with Model Context Protocol (MCP) servers, including OAuth authentication flows, resource management, and tool execution.
mcp-apache-spark-history-server
Connect AI agents to Apache Spark History Server for intelligent job analysis and performance monitoring.
opentelemetry-mcp-server
Connects AI assistants to OpenTelemetry trace backends for analyzing LLM traces with AI assistance.
2ly
2LY provides an infrastructure layer for AI agent tooling, enabling a private tool registry with embedded runtimes that integrate with various agent frameworks like LangChain, CrewAI, and AutoGPT.