catalog / DevOps & Infra / Grafana MCP Server
MCP serverDevOps & InfraFree

Grafana MCP Server

Official MCP server exposing Grafana dashboards, datasource queries, alerts, and incidents to AI agents.

Installs17k
⟳ upstream v1.1.0 · updated 7d ago
Source repository
! Grade B · 88/100 · ReviewSecurity assessment
No compromise signals23capabilities surfaced1known CVE7of 20 OWASP controls clear
Broad capability surfaceLow-confidence secret matchPotentially unbounded loopLow-confidence secret match
scanned 2d agoosv · gitleaks · opengrep · picklescan + heuristicsfull breakdown in the Security tab ↓

Grafana MCP Server

Grafana's official Model Context Protocol server connects AI agents to a Grafana instance and the observability data behind it. Instead of clicking through dashboards, an agent can search panels, query metrics and logs, and investigate alerts programmatically.

Key features

  • Search and read dashboards, panels, and their underlying queries
  • Query Prometheus and Loki datasources for metrics and logs to investigate incidents
  • Inspect and manage alert rules and firing alerts
  • Work with Grafana Incident, OnCall, and Sift investigations where configured
  • Navigate datasources and Grafana entities via a service-account API token
  • Distributed as a Go binary and container, with selectable tool groups to limit scope

By exposing Grafana as tools, it lets an assistant do real observability work — correlate a metric spike with logs, read the relevant dashboard, and summarize an alert — all through one MCP endpoint.

Curated mirror of the open-source mcp-grafana (Apache-2.0). Get it from the source.

More from @ai-supply

View profile →
Agent
MetaGPT
Multi-agent framework that assigns GPT roles (PM, engineer, QA) to solve complex software tasks end-to-end.
1.0M
Connector
vLLM
High-throughput, memory-efficient LLM inference engine with PagedAttention and continuous batching.
892k
Connector
Meilisearch
Lightning-fast open-source search engine with typo-tolerance, semantic hybrid search, and sub-50ms response times.
811k
Eval
Weights & Biases (wandb)
ML experiment tracking and visualization — log metrics, hyperparameters, models, and media in real time.
784k