Personal Data Hub
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| HUB_DATA_DIR | No | Overrides the default data directory (default is ./data). | ./data |
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 |
|---|---|
| list_tablesA | Read available table names, labels, columns and row counts. |
| describe_tableB | Read effective YAML schema; sensitive default values are masked unless reveal=true. |
| query_rowsB | Read rows, masked by default. where: FIELD OP VALUE joined by AND. Supported operators: = != > < >= <= ~. Values are parameterized. Limit 1..10000. reveal=true explicitly exposes sensitive fields and enables filtering them. |
| insert_rowC | WRITE: insert schema-validated business fields and an audit event; result is masked by default. |
| update_rowA | WRITE: update supplied fields and audit before/after values. Omitted fields survive. Optional expected_updated_at rejects stale edits. Back up before overwriting useful data. |
| delete_rowA | DELETE: remove a record only with confirm=true, preserving its reversible audit snapshot. Back up first. Audit history retains deleted sensitive data. |
| list_due_itemsB | Read upcoming and overdue documents/important dates, within a duration such as 30d. |
| get_historyC | Read change history with field-sensitive masking for both before/after snapshots. |
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 8 tools
Each tool has a clearly distinct resource and action: table introspection, row querying, row mutation, due-item listing, and history retrieval. list_due_items is specialized enough to be distinguishable from generic query_rows, and the write tools are cleanly separated by operation.
All tools follow a consistent snake_case verb_noun pattern: list_tables, describe_table, query_rows, insert_row, update_row, delete_row, list_due_items, get_history. There are no mixed casing or naming-style deviations.
Eight tools is well-scoped for a personal data hub, covering schema inspection, CRUD, due items, and audit history without obvious redundancy. Each tool earns its place in the surface.
Core row lifecycle and read paths are covered, including schema inspection, CRUD, due items, and history. Minor gaps remain: no restore/undelete operation despite reversible audit snapshots, and no bulk insert or table-level mutation tools.