MCP Supabase Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| SUPABASE_URL | Yes | The URL of your Supabase project, e.g., https://your-project.supabase.co | |
| SUPABASE_SERVICE_KEY | Yes | The service role key for your Supabase project |
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": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| supabase_queryC | Execute a SELECT query on a Supabase table with optional filtering, ordering, and pagination. |
| supabase_insertC | Insert one or more rows into a Supabase table. |
| supabase_updateC | Update rows in a Supabase table that match the filter conditions. |
| supabase_deleteC | Delete rows from a Supabase table that match the filter conditions. |
| supabase_rpcC | Call a stored function or RPC endpoint in Supabase. |
| supabase_list_tablesA | List all tables in the public schema of the Supabase database. |
| supabase_get_table_schemaB | Get column definitions and data types for a specific table. |
| supabase_upload_fileC | Upload a file to a Supabase storage bucket. |
| supabase_list_filesC | List files in a Supabase storage bucket with optional path filtering. |
| supabase_delete_fileC | Delete a file from a Supabase storage bucket. |
| supabase_list_bucketsB | List all storage buckets in the Supabase project. |
| supabase_execute_sqlC | Execute raw SQL query via RPC endpoint (requires execute_sql function to be created in Supabase). |
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 12 tools
Most tools have clearly distinct resource+action targets (query vs insert vs update vs delete, table introspection vs storage ops). The one soft spot is three overlapping 'run arbitrary logic' tools — supabase_query, supabase_rpc, and supabase_execute_sql — where an agent may hesitate between SELECT-on-table, stored function, and raw SQL, though the descriptions do differentiate them.
Every tool follows a strict supabase_<verb>_<noun> snake_case pattern (query, insert, update, delete, list_tables, get_table_schema, upload_file, list_files, delete_file, list_buckets). No deviations or mixed conventions.
12 tools is well within the ideal range and each earns its place: three DB write ops, two read/introspection paths, one RPC/SQL path, and four storage ops. Nothing feels padded or missing at the count level.
Core coverage is strong: full row-level CRUD, schema introspection, RPC/raw SQL, and storage upload/list/delete/buckets. Minor gaps remain — no bucket creation, no file download/retrieval, no upsert, and no auth/user or policy management — but these are workable around or out of the server's stated scope.