🛡️ Database Sentinel
Security audits for your database backend. Ask "audit my database" and get a scored report with exact fix code.
Works as a (Supabase, MongoDB), a for any AI client, or a that uses your own model (both Supabase).
Power your agent
การติดตั้งจากผู้เผยแพร่ ไม่ใช่เอนด์พอยต์ของ PlugMCP
URL แบบรีโมตหรือคำสั่งบนเครื่องของคุณ? การติดตั้งสองแบบต่างกันอย่างไร
รันบน PlugMCP
A new server you create. It is not this listing's official endpoint. Use the publisher install when you want their URL and their credentials.
เปิดจากผู้เผยแพร่
Security audits for your database backend. Ask "audit my database" and get a scored report with exact fix code.
Works as a (Supabase, MongoDB), a for any AI client, or a that uses your own model (both Supabase).
Open-source security audits for Supabase: a read-only MCP server, a CLI agent and a Claude Skill. Finds RLS misconfigurations, exposed keys and risky functions, and returns a scored report with fix SQL. Hosted version: Locksoup.
→ Don't want to run it yourself? Locksoup is the hosted version: a Supabase security audit with scheduled re-checks and alerts.
2026-10-01 (v1.0.1)
2026-09-30 (docs)
evals/mcp_client.py, eval system m.v1.0.0 (2026-09-30): MCP server release
audit prompt and the catalog resources. Benchmarked end to end: a model driving the server over stdio scored test F1 0.865, with critical recall 1.0.BYPASSRLS, all 20 queries.anon/authenticated revoked isn't reported as exposed.026.git+https://github.com/Farenhytee/[email protected] in any uvx/pipx command. The Claude Code plugin is pinned automatically.--deep runs the tool-using agent, which scored the same on our bench at ~5× the cost.v0.2.1 (2026-09-30)
v0.2.0 (2026-09-29)
--fix: prints fix SQL for findings you pick. It's never executed.2026-09-29
uvx --from git+… sentinel-mcp) and the agent (pipx install "database-sentinel[agent] @ git+…").sentinel-mcp --role-sql prints the read-only role setup SQL.2026-09-28
audit prompt and the pattern catalog as resources. Your own LLM does the analysis, so it's free.sentinel-audit). A LangGraph pipeline that works with any OpenAI-compatible model: OpenRouter, OpenAI, or local Ollama.Claude Code installs the audit skill and the MCP server in one go (needs uv):
claude plugin marketplace add Farenhytee/database-sentinel
claude plugin install database-sentinel@database-sentinel
Supabase users: create the read-only login (step 1), then run /plugin configure database-sentinel@database-sentinel in Claude Code. Then ask: Audit my database.
Other MCP clients, and full setup: MCP guide
Skill only (Claude Code picks it up automatically):
git clone https://github.com/Farenhytee/database-sentinel.git ~/.claude/skills/database-sentinel
CLI agent (Supabase, bring your own model):
pipx install "database-sentinel[agent] @ git+https://github.com/Farenhytee/database-sentinel"
export SENTINEL_BASE_URL=http://localhost:11434/v1 SENTINEL_MODEL=<model> # Ollama, or any OpenAI-compatible API + SENTINEL_API_KEY
sentinel-audit --dsn "postgresql://sentinel_auditor:<password>@<host>:5432/postgres" \
--rest-url https://<ref>.supabase.co --anon-key <anon key> --repo ./my-app
The default audit is one prompt plus anon-probe verification. --deep runs a tool-using agent instead: same accuracy on our bench, ~5× the cost. --fix prints fix SQL for the findings you pick; it's never executed.
Full tables are in Appendix A.
MIT. Exception: database_sentinel/agent/, database_sentinel/mcp_server/ and database_sentinel/kb/ are AGPL-3.0 (see the LICENSE in each).
Supabase
MongoDB
The MongoBleed probe (mongobleed-probe.md) is a single-packet, read-only detector. It was verified against mongo:7.0.20 (vulnerable) and 7.0.28 (patched), and runs only after two opt-in confirmations.
Only SKILL.md (~2K tokens) and core/* load up front; each backend's files load only when that backend is detected.
╔════════════════════════════════════════════════════════╗
║ SENTINEL SECURITY AUDIT ║
║ Backends: supabase Score: 35/100 🔴 ║
╚════════════════════════════════════════════════════════╝
🔴 CRITICAL — public.users: RLS Disabled [RLS_DISABLED]
Risk: Anyone on the internet can read your entire users table.
Attack: Copy the anon key from DevTools → curl the API → dump all rows.
Source: CVE-2025-48757 / Splinter 0013_rls_disabled_in_public
Fix: ALTER TABLE public.users ENABLE ROW LEVEL SECURITY;
CREATE POLICY "users_select_own" ON public.users FOR SELECT
TO authenticated USING ((SELECT auth.uid()) = id);
Prefer: tx=rollback, so no data is modified.abortTransaction() on replica sets; canary insert + delete on standalone (opt-in)..invalid email domains (RFC 6761).bench/cases/ holds labeled Supabase schemas applied to a local Supabase. evals/ scores three systems on precision, recall and F1: R0 (rules, no LLM), B0 (single prompt) and A (agent). The test split is frozen and never tuned on.
Test split (10 blind, locked cases), deepseek-v4-flash, 3 runs each:
v0.2.1 fixes the crashes and timeouts seen in the v0.2.0 test run. The fixes were diagnosed on dev only, but they came from test failures, so v0.2.0 is the blind number (v0.2.1 details). A and B0 are within noise of each other. The agent is more precise, gives fewer false alarms on clean projects and verifies findings as anon, at ~5× the cost.
pip install -e ".[dev]" && supabase start && python -m evals.run --split dev
Templates: github-action-supabase.yml and github-action-mongodb.yml. They run on migration, rule or IaC changes, weekly, or manually, then comment on the PR and fail the build on critical findings. Ask Claude: "Set up continuous security monitoring for this project."
SKILL.md, core/, backends/{supabase,mongodb}/, references/ Claude Skill (MIT)
database_sentinel/mcp_server/ MCP server (AGPL)
database_sentinel/agent/ lite agent (AGPL)
bench/, evals/, tests/, supabase/ benchmark, eval harness, local Supabase
docs/mcp.md MCP setup guide
compat/supabase-sentinel/ old skill name shim
CVE-2025-48757 (170+ Lovable apps), Escape.tech (2,000+ vulns in 5,600 vibe-coded apps), Veracode (45% of AI code has OWASP Top 10 issues), CMU SusVibes, ModernPentest (20.1M rows, 107 YC startups), Supabase Splinter lints, CVE-2025-14847 MongoBleed, Mongoose CVE-2024-53900 / CVE-2025-23061, CIS MongoDB 7 Benchmark. Full list: vibe-coding-context.md, cve-feed.md.
Most valuable: new anti-patterns with evidence (CVE, breach report, or lint), better fix templates, false-positive/negative reports from live use, and new backends following backends/supabase/. Fork, branch, and open a PR with the pattern and its source. Contributions to the AGPL directories need a CLA.
Supabase Sentinel (v1) → Database Sentinel (v3, multi-backend). The supabase-sentinel name still works through compat/supabase-sentinel/.
Open-source security audits for Supabase: a read-only MCP server, a CLI agent and a Claude Skill. Finds RLS misconfigurations, exposed keys and risky functions, and returns a scored report with fix SQ
ภาพรวม
Open-source security audits for Supabase: a read-only MCP server, a CLI agent and a Claude Skill. Finds RLS misconfigurations, exposed keys and risky functions, and returns a scored report with fix SQL. Hosted version: Locksoup.
เครื่องมือ
ยังไม่มีรายการเครื่องมือ เซิร์ฟเวอร์แบบรีโมตจะได้รายการหลังการตรวจสอบสถานะครั้งแรก
FAQ
คัดลอกคอนฟิก stdio สำหรับ Cursor, Claude Desktop, Claude Code หรือ VS Code ได้ในหน้านี้ คอนฟิกนี้ใช้การติดตั้งของผู้เผยแพร่ ไม่ใช่พร็อกซีของ PlugMCP
ระเบียนนี้ไม่ได้ระบุตัวแปรสภาพแวดล้อมที่จำเป็น
Database Sentinel ทำงานแบบโลคัลผ่าน stdio
ตรวจสอบล่าสุดเมื่อ 2026-10-26 Open-source security audits for Supabase: a read-only MCP server, a CLI agent and a Claude Skill. Finds RLS misconfigurations, exposed keys and risky functions, and returns a scored report with fix SQL. Hosted version: Locksoup.