← Leaderboard
7.5 L3

Supabase

Ready Assessed · Docs reviewed · Mar 11, 2026 Confidence 0.88 Last evaluated Mar 11, 2026

Score breakdown

Dimension Score Bar
Execution Score

Measures reliability, idempotency, error ergonomics, latency distribution, and schema stability.

8.0
Access Readiness Score

Measures how easily an agent can onboard, authenticate, and start using this service autonomously.

6.8
Aggregate AN Score

Composite score: 70% execution + 30% access readiness.

7.5

Autonomy breakdown

P1 Payment Autonomy
7.0

Free tier generous; billing API exists but limited automation

G1 Governance Readiness
7.0

RLS policies, org-level access, growing compliance certifications

W1 Web Agent Accessibility
7.0

Dashboard is clean and navigable; PostgREST API is agent-friendly

Overall Autonomy 7.0/10
Ready for agent use

Active failure modes

  • HIGH

    RLS policy silent data filtering

    Row Level Security policies silently filter results rather than returning permission errors. Agents querying with wrong auth context get empty results, not errors.

    Agent impact: Agent believes table is empty when RLS is filtering all rows. Extremely hard to debug — no error message, just missing data.

    Workaround: Always verify RLS context by testing with known-existing data. Use service_role key for administrative operations. Add explicit RLS policy tests.

    common auth
  • MEDIUM

    Connection pooler timeout on cold start

    Supabase connection pooler (pgBouncer) can timeout on first connection after idle period. Default timeout is aggressive for serverless environments.

    Agent impact: Agent's first database query after idle period fails. If no retry logic, the entire operation aborts.

    Workaround: Implement connection retry with 2-second initial delay. Use session pooler mode (port 5432) for persistent connections. Add health check pings.

    common connection

Use in your agent

mcp
get_score ("supabase")
● Supabase 7.5 L3 Ready
exec: 8.0 · access: 6.8

Trust & provenance

This score is documentation-derived. Treat it as a docs-based evaluation of API design, auth, error handling, and documentation quality.

Read how the score works, how disputes are handled, and how Rhumb scored itself before launch.

Overall tier

L3 Ready

7.5 / 10.0

Alternatives

No alternatives captured yet.