MCP Datastore Server
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
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| datastore_list_kindsA | List all available entity kinds (tables) in the Datastore |
| datastore_getC | Get an entity by its key |
| datastore_queryC | Execute a query on entities with optional filters |
| datastore_filterC | Query entities with a simple equality filter on any field |
| datastore_countC | Count entities in a kind, optionally with a filter |
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 5 tools
Most tools have distinct purposes, but datastore_filter and datastore_query overlap significantly in functionality, which could cause confusion. The other tools (count, get, list_kinds) are clearly differentiated, but the boundary between filtering and querying is ambiguous.
All tool names follow a consistent datastore_verb_noun pattern with snake_case, making them predictable and easy to understand. The naming convention is uniform across all five tools, with no deviations in style or structure.
Five tools is a reasonable number for a datastore server, providing core operations like count, get, list, filter, and query. It's slightly lean but covers essential functions without being overwhelming, though it might benefit from additional CRUD operations for completeness.
The toolset includes read operations (get, filter, query, count, list) but lacks create, update, and delete tools, which are fundamental for a datastore's lifecycle. This gap limits agents to querying and reading data without the ability to modify it, making the surface notably incomplete for full datastore management.