AutoMCP-SQL
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| DB_PATH | No | Path to the SQLite database file | ./legacy.db |
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
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| get_usersA | Get rows from users. filters = JSON string like '{"col":"val"}' or empty string for all rows. |
| create_usersA | Insert a new row into users. data = JSON string like '{"col":"val"}'. |
| update_usersA | Update a row in users by id. data = JSON string of fields to update. |
| delete_usersB | Delete a row from users by id. |
| get_productsA | Get rows from products. filters = JSON string like '{"col":"val"}' or empty string for all rows. |
| create_productsA | Insert a new row into products. data = JSON string like '{"col":"val"}'. |
| update_productsA | Update a row in products by id. data = JSON string of fields to update. |
| delete_productsA | Delete a row from products by id. |
| get_ordersA | Get rows from orders. filters = JSON string like '{"col":"val"}' or empty string for all rows. |
| create_ordersA | Insert a new row into orders. data = JSON string like '{"col":"val"}'. |
| update_ordersA | Update a row in orders by id. data = JSON string of fields to update. |
| delete_ordersB | Delete a row from orders by id. |
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
Each tool is uniquely named with a verb (get, create, update, delete) and a specific table (users, products, orders). There is no overlap because every combination of action and table is distinct and clearly indicated by the name.
All tool names follow the same verb_noun pattern using snake_case (e.g., get_users, update_products). This is perfectly consistent across the entire set, making the tools predictable and easy to navigate.
With 12 tools, the count is well-scoped for a CRUD API covering three tables (users, products, orders). Each tool serves a clear purpose, and there is no bloat or redundancy.
Each of the three tables has complete CRUD coverage: get (read with optional filters), create (insert), update, and delete. This covers all standard lifecycle operations for a SQL-based server, leaving no obvious dead ends.