"Supabase" matching MCP servers:

MCP server that lets AI coding agents (Claude Code, Cursor, Cline) audit Supabase projects for security misconfigurations AND apply the fixes — without leaving the agent. Tools: audit_project, list_findings, preview_fix (BEGIN/ROLLBACK safety), apply_fix (with confirmation), apply_all_fixes (transactional bulk). Closes the audit-fix loop entirely in the agent — other Supabase scanners only report.

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.

A local policy wrapper for Supabase MCP that secures access tokens and enforces strict execution models, including project allowlists and write-access restrictions. It provides a safety layer to prevent AI agents from accidentally executing migrations or writing SQL against production environments.

Enables AI agents to safely interact with Supabase through read-only and gated-write tools, with bounded queries, allowlists, and explicit project targeting.

Experimental read-only MCP for Supabase application data: memory_search, memory_get and memory_list_recent under user-bound PostgreSQL RLS. Setup and demo: https://github.com/jryski/Supabase_user_MCP/blob/main/docs/GETTING_STARTED.md . Public preview is POSIX-only and synthetic-only; native Windows, hosted OAuth, one-click installation and writes are not available.

Exposes your application's resources and tools as an MCP server using Supabase Auth, Postgres, and Row Level Security, allowing authorized users to connect via compatible MCP clients.

Gives Claude read-mostly, row-level-security-aware access to a Supabase or plain Postgres database through tools for inspecting roles, listing and describing tables, selecting and counting rows with structured filters, plus opt-in read-only SQL and single-row inserts. Every call runs in a read-only transaction under the anon or authenticated role with JWT claims set, so RLS policies, schema allowlists, row caps and statement timeouts apply exactly as they would for a real client.

Enables MCP clients to safely inspect and query an explicitly allowlisted subset of a Postgres database through four read-only tools: a readiness check, table listing, column description, and typed row selection with filters, ordering, and paging. It runs over stdio for local clients or Streamable HTTP for separately managed ones, with bound parameters, bounded reads, and read-only transactions.

Audits PostgreSQL/Supabase schemas for security issues like missing RLS, permissive policies, and sensitive data exposure during AI conversations.

Scan a deployed site for an exposed Supabase service_role key and audit Row Level Security from your AI coding agent.

Enables AI coding assistants to check whether an API key is safe to expose, audit Supabase Row Level Security, generate owner-based RLS policy templates, and run a builder-specific pre-launch security checklist. Runs locally over stdio with no network calls, telemetry, or file access.

Read-only MCP server for cloudpin, which pins cloud accounts (Azure, AWS, gcloud, Vercel, GitHub, Kubernetes, Supabase, Cloudflare) to a repository. Its tools tell an agent which account each CLI is using and whether a command would run on the pinned one, before it acts.

Lets an MCP client triage a local project for leaked secrets, missing Supabase row-level security, unauthenticated data-changing API routes, insecure browser-exposed environment variables, and other common web-app security mistakes without network access. It returns severity-ordered findings or a plain-English go/no-go summary with what to fix first.

Security MCP server with 300+ rules for AI-generated code. Scans Next.js, Supabase, Clerk, Stripe, Prisma, Hono, GraphQL and 20+ modules. Zero config, runs locally.

Read-only security audit for Supabase. Surfaces RLS gaps, permissive policies, exposed functions and grants, and returns scored findings with fix SQL that is never executed.

Predeploy security scanner for AI-generated code. 80+ vulnerability patterns across secrets, auth, injection, config, Supabase, and logging. Runs locally, code never leaves your machine. Optional x402 witnessed attestation.

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.

Local, encrypted credential vault for AI agents that enables secure multi-account management across services like Supabase, GitHub, Vercel, and Stripe, allowing seamless account switching without restarting the chat client.

Enables safe, read-only SQL exploration and debugging on Supabase Edge Functions, respecting user JWTs. It inspects schemas, explains query plans, proposes RLS policies, and runs guarded queries without destructive operations.

A self-hosted MCP server that mints, places, and rotates cloud secrets (e.g., Cloudflare, GitHub, Supabase) without exposing secret values to the agent, using a signed destination allow-list and self-maintaining rotation.