Score breakdown
Popularity is tracked separately. Support, ads, sponsorships, and tips never affect these signals.
Why it matters
Useful for SRE and platform teams who want an LLM agent to answer 'what did the dashboards and logs look like during the incident' by querying Grafana directly instead of asking a human to screenshot panels, for observability engineers building agentic runbooks that need a maintained first-party MCP surface over Prometheus and Loki rather than a community wrapper that lags Grafana releases, and
Where this stands now
grafana/mcp-grafana ranks #5 of 12 tracked MCP Servers items by composite score (7.9 against a section median of 7.8). The section currently carries 5 Silver, 4 Gold, 3 Bronze. RepoRadar has retained observations for this record since 2026-08-17 (56 days in the current window). Signal extremes versus the section: novelty at the 4th percentile.
Who should use it
Who should skip it
Pass on grafana/mcp-grafana if its scope or audience does not match what your team is building right now.
About this signal
grafana/mcp-grafana is tracked by RepoRadar as a developer tool in the MCP Servers section. First seen 2026-08-17; the source record was last checked on 2026-08-17. The current verdict is 'try now' with a Gold tier and easy setup difficulty. Across RepoRadar's eight signals, grafana/mcp-grafana is strongest on workflow potential (9.4) and maturity (8.7) and weakest on novelty (6.6) — a profile worth weighing against your own priorities. This page summarizes the evidence RepoRadar captured from https://github.com/grafana/mcp-grafana.
How this item is evaluated
The grafana/mcp-grafana record combines a 7.9/10 composite score with separate popularity (100.0), risk (low), and setup (easy) signals. See the scoring methodology for the current weights and evidence definitions.
Questions worth asking before you adopt this
Putting this into practice? Read How to vet an AI agent or MCP server before you wire it in for the checklist behind this score.
Risk explanation
Requires a Grafana service account token with real access to your observability stack; scope it to read-only viewer permissions on the narrowest folder set that answers your questions, and rotate it like any other production credential; Read access to production dashboards, metrics and logs can pull sensitive operational or customer data into model context -- confirm your model provider's data handling posture before pointing this at production Grafana; Broad backend query surface (CloudWatch, Snowflake, Athena, ClickHouse, Elasticsearch and more) is available; it is disabled by default and gated behind explicit --enabled-tools, so keep it that way and enable one group at a time rather than enabling everything; The agent-observability tool group works only on Grafana Cloud and its write operations require the Agento11y Admin role -- verify which of your environments can actually use it before designing a runbook around it.