Metabase
Enables teams to access business intelligence and analytics through conversational queries without SQL expertise, reducing time spent on data request bottlen…
Lets Claude query Metabase data via natural language — search tables/metrics, explore field values, and build or run queries — with results scoped to the connecting user's own Metabase permissions.
- Ask Claude to find which customers generated the most revenue last quarter
- Generate a sales report by region without writing SQL manually
- Explore available data fields to understand what metrics exist in your database
Enables teams to access business intelligence and analytics through conversational queries without SQL expertise, reducing time spent on data request bottlenecks and accelerating insight generation for decision-making.
Data-driven engineering teams and business analysts needing rapid access to metrics, performance data, and operational dashboards respecting existing permission controls.
https://claude.com/connectors/metabase
By Metabase
How to Get It
Once it’s connected, paste this into Claude:
Find which customers generated the most revenue last quarter
Trust Signals Auto-scanned
Not yet scanned. Learn how to check this tool yourself.
Data & Access
Community Pulse New
No community discussions found yet. This doesn't mean the tool isn't good — it may be new or serve a niche use case.
Reviewer notes
Auto-scanned review. These are observations, not a security certification.
NOTE ON SCOPE: the task prompt for this dispatch arrived corrupted/truncated (only 'cts Cl' survived, no tool list). Reconstructed the intended 6 slugs from shared scratchpad evidence (eval_input.json + coverage cross-check across every prior batch this session) — see /scratchpad/batch8/NOTES.md for the full trace. Metabase itself: official docs (metabase.com/docs/latest/ai/mcp) confirm OAuth 2.0 via Metabase's own embedded OAuth server (no external IdP needed), results scoped to the connecting user's existing Metabase permissions, and GA status as of Metabase v0.63 (admin must explicitly enable it instance-wide). Write tools exist (create/update collections, dashboards, questions, and SQL execution if the admin allows it) but inherit the user's own permission ceiling, which is a sound least-privilege design. | Sentiment: No significant community signal found — WebSearch budget exhausted session-wide (200/200), firecrawl at 0 credits, consistent with every prior batch this session. | Ensemble: median of 14 independent doc+sentiment evaluations (official-coverage sweep 2026-07-23).
Things to check
- Requires Metabase v0.63+ and an admin to explicitly enable both AI features and the MCP server instance-wide; not a zero-config connect. WebSearch sentiment unavailable (session budget exhausted, confirmed on this query); firecrawl at 0/1000 credits, evaluated via WebFetch on the official connector page + docs.
How to evaluate tools before deploying →
Data shown here comes from public APIs and automated scanning. Reviewer notes reflect one person's experience. This is not a security certification or legal recommendation. Always evaluate tools according to your own organization's policies.
Evaluation
NOTE ON SCOPE: the task prompt for this dispatch arrived corrupted/truncated (only 'cts Cl' survived, no tool list). Reconstructed the intended 6 slugs from shared scratchpad evidence (eval_input.json + coverage cross-check across every prior batch this session) — see /scratchpad/batch8/NOTES.md for the full trace. Metabase itself: official docs (metabase.com/docs/latest/ai/mcp) confirm OAuth 2.0 via Metabase's own embedded OAuth server (no external IdP needed), results scoped to the connecting user's existing Metabase permissions, and GA status as of Metabase v0.63 (admin must explicitly enable it instance-wide). Write tools exist (create/update collections, dashboards, questions, and SQL execution if the admin allows it) but inherit the user's own permission ceiling, which is a sound least-privilege design. | Sentiment: No significant community signal found — WebSearch budget exhausted session-wide (200/200), firecrawl at 0 credits, consistent with every prior batch this session. | Ensemble: median of 14 independent doc+sentiment evaluations (official-coverage sweep 2026-07-23).