pxweb-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| PXWEB_URL | No | URL of the PxWeb API v2 instance (e.g., https://data.ssb.no/api/pxwebapi/v2). | https://data.ssb.no/api/pxwebapi/v2 |
| PXWEB_PORT | No | Port for HTTP transport when using streamable-http. | 3000 |
| PXWEB_TRANSPORT | No | Transport protocol (e.g., stdio or streamable-http). | stdio |
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 |
|---|---|
| search_tablesA | Search for tables in Statistics Norway (SSB) database. Supports wildcards (*) at end of words, boolean operators (AND, OR), and special filters:
Geographic indicators in titles: (F) = county, (K) = municipality, (B) = city district. |
| get_table_infoA | Get basic information about a table (title, time range, variables). Use this for a quick overview before fetching full metadata. |
| fetch_metadataA | Fetch detailed metadata for a table to understand its structure. Returns variable IDs, value codes, elimination info, and available code lists. Use this to construct queries. |
| query_tableB | Query data from a table using the v2 API syntax. Value selection syntax:
Output formats: json-stat2, csv, xlsx, html, px, json-px For csv/xlsx/html, use stub and heading to control layout. |
| get_code_listA | Fetch a code list (valueset or grouping). Valuesets (vs_*): Lists of valid values for a variable. Groupings (agg_*): Aggregation mappings (e.g., municipality mergers). Find available code lists in table metadata under 'codeLists'. |
| list_recent_tablesA | List tables updated in the past N days. Use this to find newly published statistics. |
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
Tools are mostly separable: search_tables and list_recent_tables both discover tables but use different criteria, and query_table/get_code_list have unique roles. The only mild overlap is get_table_info versus fetch_metadata, where the descriptions distinguish basic overview from detailed query-building metadata.
All tool names follow the same verb_noun snake_case pattern (search_tables, query_table, get_code_list, etc.). The use of fetch instead of get in fetch_metadata is a minor synonym variation but does not break the overall pattern.
Six tools is a well-scoped size for a statistical data server, covering discovery, metadata inspection, code lists, and querying. Each tool has a distinct role and none feels like filler.
The tool set supports the full user workflow: find tables, inspect metadata, resolve code lists, and query data. For a read-only public statistics API, there are no obvious missing operations that would create dead ends.