supabase-rls-check
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| analyze_sql_exportA | Validate and summarize a local CSV or JSON metadata export from check.sql. |
| explain_ruleB | Explain what a supabase-rls-check rule detects, caveats, and how to remediate it. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 2 tools
The two tools operate on completely different inputs: one validates/summarizes a local metadata export file, the other returns static documentation for a rule. There is no plausible way for an agent to confuse them.
Both names use the same snake_case verb_noun pattern (analyze_sql_export, explain_rule) with clear, specific nouns. No stylistic drift between the two.
Two tools is thin for a domain that includes running the check, enumerating rules, and interpreting results. It is defensible given a narrow scan-and-explain scope, but the surface feels minimal rather than well-scoped.
There is no way to list available rules (so explain_rule requires guessing rule names) and no tool to actually run or re-run check.sql, only to analyze a pre-existing export. Remediation is described in prose via explain_rule but never produced as SQL, leaving notable dead ends.