"Accessing Your Supabase Projects Dashboard" 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.

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.

Security Graph MCP Server

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

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.

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.

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.

Visual CVE audit dashboard for npm, Python, Go, and Rust projects. Scans your project manifests (package-lock.json, requirements.txt, go.sum, Cargo.lock) against OSV.dev live data, opens a browser dashboard for human review, then applies fixes only after explicit confirmation. Supports multi-service monorepos in one command.

A local-first MCP server that scores your codebase's Build Readiness by reading code and running tests on your machine, outputting a diligence-grade score and risk register without uploading your source.

Give Claude secure access to your accounts.

Blocks AI coding assistants from installing non-existent packages and accessing non-existent files.

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.

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

Enables scanning Java (Maven) projects for known vulnerabilities via natural language, returning severity-sorted reports with CVSS scores and fix versions.

Scaffold and audit Starter Series projects — MCP server, Claude Code skill, and CLI in one package.

Cryptographic accountability for AI agents. Ed25519-signed receipts for every MCP tool call. Constraints, chains, AI judgment, invoicing, and local dashboard included.

Scans projects for hardcoded secrets, unprotected .env files, and console.log leaks to prevent credential exposure.

A demonstration server that reveals security risks by accessing sensitive environment variables, illustrating how MCP tools can potentially leak user data without explicit consent.

ai-runtime-guard is an MCP server that sits between your AI agent and your system, enforcing a policy layer before any file or shell action takes effect. No retraining, no prompt engineering, no changes to your agent or workflow, just install, configure once, and your agent operates within the boundaries you set.

Enables MCP-capable LLM agents to control YADS queues, manage tags, and trigger scans through YADS's API-authenticated /api/v1 interface without dashboard access. All actions respect tenant isolation and scan limits.