Supabase NextJS MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| NEXT_PUBLIC_SUPABASE_URL | Yes | The URL of your Supabase instance | |
| NEXT_PUBLIC_SUPABASE_ANON_KEY | Yes | The anonymous key for your Supabase instance |
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 | {} |
| resources | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| query_dataC | Query data from Supabase |
| insert_recordC | Insert a record into Supabase |
| update_recordC | Update a record in Supabase |
| delete_recordC | Delete a record from 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 4 tools
Each tool has a clearly distinct purpose targeting a specific CRUD operation: delete, insert, query, and update. There is no overlap or ambiguity between these fundamental database operations, making tool selection straightforward for an agent.
All tool names follow a consistent verb_noun pattern (delete_record, insert_record, query_data, update_record) with perfect uniformity. The naming convention is predictable and readable throughout the set.
With exactly 4 tools covering the core CRUD operations for a database server, this is well-scoped and appropriate. Each tool earns its place with no redundancy or missing essentials for basic data manipulation.
The tool set provides complete CRUD coverage for the Supabase database domain: create (insert), read (query), update, and delete. There are no obvious gaps for basic data operations, ensuring agents can handle full lifecycle workflows without dead ends.