Grafana
The Grafana MCP Server provides AI assistants with direct access to Grafana's monitoring and observability capabilities through a comprehensive set of tools for querying metrics, logs, and dashboard data. Built by DrDroidLab, it supports PromQL queries against Prometheus datasources, Loki log queries, dashboard panel execution with template variable support, and metadata retrieval for datasources, folders, and dashboards. The server optimizes time series data to reduce token usage, handles both HTTP and STDIO transports, and includes Docker deployment options with configurable authentication via API keys or environment variables, making it valuable for DevOps workflows, incident response, performance monitoring, and automated observability analysis where AI agents need real-time access to infrastructure metrics and logs.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately.
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- cloud-infra
- Source
- PulseMCP
- Repository
- github.com/drdroidlab/grafana-mcp-server
- Author type
- human
- Updated
- 2026-04-25
Use via MCP
Resolve Grafana from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp--scope user for --scope project to commit it to .mcp.json.