Check Supabase migrations for RLS and grant gaps; fixes for Supabase, Vercel, Stripe errors.
io.github.ohad6k/viberaven-guides — MCP Server
This MCP server provides read-only access to VibeRaven guides. It explains a finding, supports searching for launch guides, and can retrieve a Supabase checklist. The server is identified by the slug io-github-ohad6k-viberaven-guides and is scoped to guide content only.
🛠️ Key Features
Read-only VibeRaven guides
Explain a finding
Search launch guides
Get a Supabase checklist
🚀 Use Cases
Look up explanations for a specific VibeRaven finding
Review Supabase migration changes for missing RLS or policies, unrestricted read/write policies, exposed security definer functions and Data API grant gaps. Pass file contents: sql contains one migration's SQL text; files contains path and content for each file. Runs the VibeRaven 1.6.12 SQL rules and returns finding id, severity, file, line, a suggested fix and a guide link. For missing Data API grants, include the migration revoking default privileges or supabase/config.toml, plus browser files using supabase.from(...) (a "use client" file, or src files with package.json for Vite).
Limits: supplied text only, up to 200 KB/50 files; cannot access your repository or database, does not execute SQL, and does not store or log file contents.
Parameters2
sql
string
optional
The SQL text of one migration file.
files
array
optional
Several files: .sql migrations, and optionally supabase/config.toml, package.json and browser code files.
Raw schema
{
"type": "object",
"properties": {
"sql": {
"type": "string",
"minLength": 1,
"description": "The SQL text of one migration file."
},
"files": {
"type": "array",
"minItems": 1,
"maxItems": 50,
"items": {
"type": "object",
"properties": {
"path": {
"type": "string",
"minLength": 1,
"maxLength": 300,
"description": "The file path in the repo, for example supabase/migrations/20260101000000_init.sql. Migrations run in file name order."
},
"content": {
"type": "string",
"description": "The full text of the file."
}
},
"required": [
"path",
"content"
],
"additionalProperties": false
},
"description": "Several files: .sql migrations, and optionally supabase/config.toml, package.json and browser code files."
}
},
"additionalProperties": false,
"oneOf": [
{
"required": [
"sql"
]
},
{
"required": [
"files"
]
}
]
}
provider_playbook
Plan setup and integration before implementing a feature that touches a provider. Returns versioned setup guidance, gotchas, dated changes, integration seams, existing repo checks and planned live checks with official sources. Available packs: supabase.
Limits: guidance only; does not connect to providers, read your project, run checks or verify that a feature works.
Parameters1
provider
string
required
Provider id, for example supabase. Unsupported ids return the available packs.
Raw schema
{
"type": "object",
"properties": {
"provider": {
"type": "string",
"minLength": 1,
"maxLength": 40,
"pattern": "^[a-z][a-z0-9-]*$",
"description": "Provider id, for example supabase. Unsupported ids return the available packs."
}
},
"required": [
"provider"
],
"additionalProperties": false
}
explain_finding
Understand and fix a finding from a VibeRaven 1.6.12 report, such as rls_disabled or env_var_drift. Returns detection scope, impact, fix guidance and coverage limits quoted from viberaven.dev with source links. Known ids: rls_disabled, rls_no_policies, rls_policy_allows_all_read, rls_policy_allows_all_write, security_definer_function_executable, pooler_port_mismatch, service_role_key_in_client_code, env_var_drift. Unknown ids return found: false and known ids.
Limits: explains published rules only; does not read your repo, database or Vercel project.
Parameters1
gap_id
string
required
The finding id as printed by VibeRaven, for example rls_disabled.
Raw schema
{
"type": "object",
"properties": {
"gap_id": {
"type": "string",
"minLength": 1,
"maxLength": 100,
"description": "The finding id as printed by VibeRaven, for example rls_disabled."
}
},
"required": [
"gap_id"
],
"additionalProperties": false
}
search_guides
Find troubleshooting steps for Supabase RLS, Realtime and auth callbacks, Vercel environment variables and deployment errors, or Stripe webhooks after deploy. Search published viberaven.dev guides by keyword; returns up to 5 titles, URLs and short answers. Also covers Lovable + Supabase launch checks and client handoff. No match returns an empty list.
Limits: searches the indexed published guides only; does not browse the web or read your project.
Parameters1
query
string
required
A few keywords from the question, for example "supabase tables missing rls".
Raw schema
{
"type": "object",
"properties": {
"query": {
"type": "string",
"minLength": 1,
"maxLength": 200,
"description": "A few keywords from the question, for example \"supabase tables missing rls\"."
}
},
"required": [
"query"
],
"additionalProperties": false
}
launch_checklist
Prepare a Lovable + Supabase app or a Next.js + Supabase app on Vercel for launch. Returns a published manual checklist with sources and an optional local repo check (`npx -y viberaven@1.6.12 check`).
Limits: checklist guidance only; does not run checks or verify dashboards, code or launch readiness.
Parameters1
stack
string
required
lovable-supabase for a Lovable app with Supabase, nextjs-supabase-vercel for a Next.js app with Supabase deployed on Vercel.
Raw schema
{
"type": "object",
"properties": {
"stack": {
"type": "string",
"enum": [
"lovable-supabase",
"nextjs-supabase-vercel"
],
"description": "lovable-supabase for a Lovable app with Supabase, nextjs-supabase-vercel for a Next.js app with Supabase deployed on Vercel."
}
},
"required": [
"stack"
],
"additionalProperties": false
}
The production layer for AI-built apps.
Checks across Supabase, Vercel and Stripe, and an engine that races every rule in your database on real PostgreSQL, before your users do.
The engine inside VibeRaven, on the bundled example:
sh
npx -y viberaven@1.10.0 race --example
text
At most 2 bookings per event: 60 orders, 24 broken, 0 waiting; 1.495s total
read committed: 12/20 broken
repeatable read: 12/20 broken
serializable: 0/20 broken
First broken order 001101 (read committed); COMMIT A=true, B=true
Replay record is byte-identical, including PostgreSQL protocol bytes.
That is the engine inside VibeRaven: race tests your app's database with two users at once, on real PostgreSQL, without Docker, and replays exactly what broke. In order 001101, A inserts, B inserts, A commits, B commits: the event ends with 3 bookings out of 2. The bundled fix brings it to 0 broken of 60.
npx -y viberaven race --example: two users book the last seat at once. 12 orders broke under read committed, 12 under repeatable read, 0 under serializable: 24 of 60. The broken order replays exactly.
Inside your chat
Add https://viberaven.dev/mcp as a custom connector in ChatGPT, Claude, Codex, Cursor or Lovable, then ask: "Can two users book the last seat?" Setup for each agent.
In your repo
sh
npx -y viberaven@1.10.0 check # what is risky before launch
npx -y viberaven@1.10.0 race # what breaks when two users act at once
check reads migrations, client code and env files, and names the file and line for each gap.
race runs the rule in your viberaven.race.json: setup, two requests and the SQL that must stay true. Spec template.
Fix, run race again, and replay the reported order. Exit 0: no order broke. Exit 1: broken. Exit 2: incomplete.
race needs Node 24+ (the CLI enables JSPI). check runs on Node 20+.
Add https://viberaven.dev/mcp as a custom connector
Local MCP tools: npx -y @viberaven/mcp@1.10.0. Details in the agent hub.
Building an agent that answers provider errors? The AI SDK provider-context example adds search_guides and recent_provider_changes from the hosted MCP endpoint.
Local Studio
npx -y viberaven@1.10.0 opens the local Studio: chat with your coding agent, the provider board, versions and diffs, and a Race test tab that runs race and replays a broken order.
check reads the repository. It does not show which policies are live in Supabase or Vercel, and a clear result is not a security audit.
race covers the SQL, inputs and bounded statement orders you supply. Rules beyond a simple count limit need an explicit spec. Omitted roles run as postgres.
An incomplete run is not a pass. Replay needs the same migrations, spec, options and runtime.
Cloud Auth, HTTP and external I/O are outside the test. Run only SQL you trust; the engine is not a security sandbox.
No universal PostgreSQL compatibility, and no advantage over a plain coding agent in bug finding, is claimed.