mcp-ssb
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| SSB_DB | No | Override the location of the SQLite database (default: ~/.local/share/mcp-ssb/ssb.db) | |
| XDG_DATA_HOME | No | Override the base data directory; the index will be placed at $XDG_DATA_HOME/mcp-ssb/ssb.db (default: ~/.local/share) |
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 |
|---|---|
| searchA | Søk i SSBs 3 898 tabeller på tittel, beskrivelse og dimensjonsnavn. Søket er bygget for norsk: det oversetter dagligtale til SSBs egne termer
(«boligpris» finnes ikke — tabellen heter «Prisindeks for brukte boliger»),
og trapper opp fra eksakte ord via prefiks til stamme til det gir treff.
Feltet Bruk |
| tableA | Hvilke dimensjoner en tabell har, og hvilke koder hver av dem godtar.
Bruk dette før Dimensjoner merket |
| dataA | Henter tall med et eksplisitt utvalg per dimensjon. Kjør
|
| latestA | Snarvei for «hva er tallet nå». Velger første statistikkvariabel, de siste N periodene, og lar SSB summere over dimensjoner som kan utelates. Dimensjoner som må settes får sin første verdi — de listes i svaret som |
| statusA | Når tabellkatalogen sist ble hentet, og hvor mange tabeller den inneholder. |
| syncA | Laster ned hele SSBs tabellkatalog og bygger indeksen om. Tar noen sekunder. En systemd-timer gjør dette ukentlig. |
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 6 tools
The six tools map to distinct stages in the workflow: discovery (search), schema lookup (table), explicit queries (data), quick latest values (latest), and catalog maintenance/status (status/sync). Even though data and latest both return numbers, latest is clearly framed as a convenience shortcut, so an agent should not confuse them.
All names are lowercase single words, so the style is uniform and there is no case or convention mixing. The semantic pattern is less regular, however: some are verbs (search, sync), some are nouns (table, data, status), and latest is an adjective, and none follow a verb_noun shape.
Six tools is appropriate for a read-only statistics API: discovery, metadata, query, convenience access, and catalog health/maintenance are each represented without redundancy. The count feels well-scoped for the server's purpose.
The core workflow is complete: search finds a table, table exposes dimensions and codes, data fetches specific selections, and latest covers a common shortcut; status and sync handle catalog freshness. The only minor gap is a lack of any browse/list-all-tables capability, but search is clearly designed to cover discovery.