VibeRaven

Check a public GitHub repo for Supabase RLS gaps

check_github_repo

Read-onlyIdempotent

check_github_repo({"repo":"owner/name"}) Check the Supabase migrations of a public GitHub repository for missing RLS or policies, policies that let anyone read or write every row, exposed security definer functions and Data API grant gaps. Use it when the user names or links their app repo (Lovable, Bolt, v0 and Cursor apps synced to GitHub) and has no terminal. Reads supabase/migrations/*.sql at one commit with the VibeRaven 1.8.0 SQL rules and returns finding id, severity, file, line, a link to that line, a fix and a guide link. Limits: public repositories only, up to 50 files/200 KB; cannot see the live database or private repos, does not run SQL, and does not store files.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "repo": "<repo>"
    },
    "name": "check_github_repo"
  }
}

Input Schema

Name	Required	Description	Default
`ref`	No	Optional branch, tag or commit. Default: the default branch.
`repo`	Yes	The public GitHub repository: https://github.com/owner/name, github.com/owner/name or owner/name.

Output Schema

Name	Required	Description	Default
`scope`	Yes
`counts`	Yes
`skipped`	Yes
`findings`	Yes
`nextStep`	No
`sql_files`	Yes
`full_check`	Yes
`repository`	Yes
`public_tables`	Yes
`viberaven_version`	Yes
`findings_not_listed`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedNov 5, 2026
- addedOutput schema / properties / nextStep / properties / codingAgentTask
```
Added value: +{
+  "type": "string"
+}
```

Changed5 schema fields changedNov 5, 2026

addedOutput schema / properties / counts / properties / needs_runtime_check
```
Added value: +{
+  "type": "integer"
+}
```

changedOutput schema / properties / counts / required

Previous value: -[
-  "critical",
-  "high",
-  "warning",
-  "info"
-]New value: +[
+  "critical",
+  "high",
+  "warning",
+  "info",
+  "needs_runtime_check"
+]

changedOutput schema / properties / findings / items / properties / id / enum

Previous value: -[
-  "rls_disabled",
-  "rls_no_policies",
-  "rls_policy_allows_all_read",
-  "rls_policy_allows_all_write",
-  "security_definer_function_executable",
-  "data_api_grant_without_rls",
-  "data_api_grant_missing"
-]New value: +[
+  "sql_needs_runtime_check",
+  "rls_disabled",
+  "rls_no_policies",
+  "rls_policy_allows_all_read",
+  "rls_policy_allows_all_write",
+  "security_definer_function_executable",
+  "data_api_grant_without_rls",
+  "data_api_grant_missing"
+]

changedOutput schema / properties / findings / items / properties / severity / enum

Previous value: -[
-  "critical",
-  "high",
-  "warning",
-  "info"
-]New value: +[
+  "critical",
+  "high",
+  "warning",
+  "info",
+  "needs_runtime_check"
+]

addedOutput schema / properties / findings / items / properties / verifyCommand
```
Added value: +{
+  "type": "string"
+}
```

Changed3 schema fields changedNov 4, 2026

addedOutput schema / properties / repository / properties / files_not_read
```
Added value: +{
+  "minimum": 0,
+  "type": "integer"
+}
```
addedOutput schema / properties / repository / properties / tree_truncated
```
Added value: +{
+  "type": "boolean"
+}
```

changedOutput schema / properties / repository / required

Previous value: -[
-  "url",
-  "commit",
-  "files_read",
-  "report_url"
-]New value: +[
+  "url",
+  "commit",
+  "files_read",
+  "files_not_read",
+  "tree_truncated",
+  "report_url"
+]

Changed2 schema fields changedNov 3, 2026

addedOutput schema / properties / repository / properties / report_url
```
Added value: +{
+  "type": "string"
+}
```

changedOutput schema / properties / repository / required

Previous value: -[
-  "url",
-  "commit",
-  "files_read"
-]New value: +[
+  "url",
+  "commit",
+  "files_read",
+  "report_url"
+]

AddedNov 3, 2026

TDQS

A4.6/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnly, idempotent, open-world and non-destructive, and the description still adds substantive behavior: which file glob is read, that it is a single commit, that it does not run SQL, does not touch the live database, does not store files. Scope limits (public repos only, 50 files/200 KB) and the finding payload are also disclosed, all consistent with readOnlyHint.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Dense and front-loaded: purpose, trigger, mechanics and limits in order. The opening `check_github_repo({"repo":"owner/name"})` call-syntax line partly duplicates the schema and is the one piece of avoidable weight.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists and annotations cover the safety profile, yet the description still summarizes the returned finding fields and states the hard limits (public only, size cap, no live DB, no SQL execution). Nothing an agent needs to decide or call correctly is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, but the phrase 'reads supabase/migrations/*.sql at one commit' adds real meaning: it tells the agent that the optional ref selects a single snapshot rather than a history scan. The accepted repo URL forms are already in the schema, so no further credit there.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource: checks the Supabase migrations of a public GitHub repository for missing RLS, permissive policies, security definer exposure and Data API grant gaps. The enumerated finding categories make it unambiguous against sibling tools that operate on local migrations or guides.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives an explicit trigger: 'use it when the user names or links their app repo ... and has no terminal', which implicitly separates it from a local-migrations tool. It does not name an alternative sibling outright, so the routing is clear but not fully closed.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All VibeRaven tools Inspect

Try in Browser

Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.