Skip to main content
Glama

Server Details

Runs an eight-stage isolation test against your staging Supabase and issues a signed attestation.

If you are the author of this connector, you can claim ownership. Claimed connector authors can inspect health checks, view analytics, and manage their listing.
Status
Healthy
Uptime
100.0% over the last 24 hours
Last Tested
Transport
Streamable HTTP · MCP 2025-11-25
URL
ChatGPT
–
Claude
–

TDQS

A3.9/5.0

Scored across 7 tools

Disambiguation4/5

The set is largely distinct: list_projects, run_review and verify_attestation target clearly different actions. The only real overlaps are get_findings vs get_report (both read a completed run's output, though descriptions explicitly separate compact view from full signed JSON) and get_run_status vs wait_for_run, whose descriptions admit wait_for_run returns the same information as get_run_status.

Naming Consistency5/5

Every tool follows a strict snake_case verb_noun pattern (get_findings, get_report, get_run_status, list_projects, run_review, verify_attestation, wait_for_run). The verbs are predictable and map cleanly to read/act semantics, with no camelCase or stylistic mixing.

Tool Count5/5

Seven tools is well within the ideal range and every one earns its place in a single workflow: discover project, start run, poll/wait, retrieve findings, retrieve report, verify external attestation. Nothing feels redundant or padded.

Completeness4/5

The core lifecycle — project discovery, run creation, status polling/waiting, findings, signed report and third-party verification — is fully covered with no dead ends. Minor gaps exist: no way to list run history per project, cancel/abort an in-flight run, or manage project connections, which an agent may occasionally need.

Available Tools

7 tools
get_findingsA
Read-only
Inspect

Returns the cells that did not pass in a complete run that has a signed report — verdict, surface, operation, boundary, identity, layer outcomes and notes — plus tenancy flags, blocking findings and, when the report includes catalog hygiene checks, the hygiene block (the checks run, each finding's check, severity, object, detail and hint, and any check not run). For a complete run with no signed report, while one can still be bought on the run page, it returns the run's unverified result instead: the verdict, surface, operation and principal of each cell that did not pass, the run page's finding lines, the counts, the coverage lines, the access model summary and the same hygiene block. The list of cells is empty when every tested cell passed. Cell results contain no fix suggestions: the engine records only what it observed. Hygiene findings are catalog observations, never verdicts; each carries the engine's one-line hint for the project owner's review.

Inputs: run_id (required).

get_reportA
Read-only
Inspect

Returns the full signed report of a complete run as the exact stored JSON, with its verify_url and report_sha256 (sha256 of the canonical signed bytes, the fingerprint shown on the verify page). Use get_findings for the compact view.

Inputs: run_id (required).

get_run_statusB
Read-only
Inspect

Returns a run's status (queued, running, complete or failed), its current stage, timestamps and, when a signed report exists, its verify_url.

Inputs: run_id (required).

list_projectsA
Read-only
Inspect

Lists the Supabase projects connected to this account with id, name, connection state and whether each is ready to run. Call this first to get a project_id.

Inputs: no named parameters.

run_reviewAInspect

Starts an authorization test run on a connected project and returns the run_id and status. If the project already has a run waiting to start, returns that run instead of starting another. Runs that do not fail count against the monthly allowance.

Inputs: project_id (required), label, attest.

verify_attestationA
Read-only
Inspect

Checks a RowAttest attestation published by a site or MCP server. Give it the origin (for example https://example.com); it fetches /.well-known/rowattest.json there, follows the first entry to the signed summary, verifies the signature offline against RowAttest's public key list, and returns whether the proof is valid, when it was issued, its totals, whether findings were present, and whether it is bound to the project ref you pass. It reads public data only, needs no project of yours, and starts no run. A valid proof means the listed checks ran at that time and were signed by RowAttest; it does not mean the application is secure.

Inputs: origin (required), fingerprint, project_ref.

wait_for_runA
Read-only
Inspect

Waits up to timeout_seconds (1 to 60) for a run to finish, then returns the same information as get_run_status. Call it again while the status is still queued or running.

Inputs: run_id (required), timeout_seconds.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      C
      maintenance
      Enables AI coding agents to audit Supabase or Postgres databases for Row Level Security and multi-tenant isolation holes, reading tables, grants, policies and functions for static findings and optionally probing those policies inside a rolled-back transaction. It reports each hole with an explanation and a fix, so an agent can verify the migrations it just wrote before declaring them done.
      1
      MIT
    • A
      license
      A
      quality
      B
      maintenance
      Enables auditing a Supabase project's security beyond the dashboard's Security Advisor, checking anonymous access, RLS policies, and cross-tenant data leaks via read-only probes and a two-account test.
      4
      16 npm
      MIT
    • A
      license
      Not graded
      quality
      B
      maintenance
      Lets coding agents ask whether a Supabase migration is safe to merge: it replays the base branch and working tree into throwaway databases, reports only the findings the change introduces, and proves RLS leaks by querying as anon. Tools are read-only and take profile names instead of connection strings.
      16 npm
      MIT
    Try in Browser

    Glama MCP Gateway

    Add one secure layer between your agents and this server.

    Resources