data-bs-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| DATA_PORTAL_DOMAIN | Yes | The domain of the Huwise/Opendatasoft data portal (e.g., data.bl.ch). Used to build the API base URL. |
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_datasetsA | Search and list available open datasets from data.bs.ch. Two modes: 'semantic' (default) ranks the catalog by meaning using natural-language queries (handles synonyms and other languages); 'lexical' does a classic full-text match on the exact terms. Use semantic for conceptual discovery, lexical for precise term/name lookups. |
| get_datasetA | Get detailed metadata for a specific dataset including field definitions, schema, publisher info, and record count. Use this to understand a dataset's structure before querying records. |
| get_recordsA | Query and filter records from a dataset using ODSQL syntax. Use this to retrieve actual data from a dataset with optional WHERE clauses, ordering, and pagination. |
| get_facetsB | Get available filter values for categorizing datasets. Useful for discovering publishers, keywords, themes, or other facets to refine dataset searches. |
| export_dataset_urlA | Generate a download URL for exporting a dataset in various formats (CSV, JSON, GeoJSON, XLSX, Shapefile, Parquet, etc.). Use this when you need to download or share dataset exports. |
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
Each tool targets a distinct stage: search (get_datasets), metadata (get_dataset), facets (get_facets), records (get_records), and export (export_dataset_url). Minor potential confusion exists between get_datasets and get_facets for discovery, but descriptions clarify their different purposes.
All tools follow a verb_noun pattern, with four using 'get_' and one using 'export_', both being clear verbs. The naming is consistent and predictable across the set.
Five tools is well-scoped for a data portal: search, metadata, facets, records, and export cover the core read workflows without unnecessary bloat.
The set covers the full read lifecycle: discover datasets, understand their structure, query records, and export data. No obvious missing operations for a public read-only open data portal.