mcp-nbb
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| NBB_ORIGIN | No | Origin header required for the upstream WAF. | https://dataexplorer.nbb.be |
| NBB_LOG_LEVEL | No | Log level: DEBUG, INFO, WARNING, or ERROR. | INFO |
| NBB_LOG_FORMAT | No | Log format: json or console. | json |
| NBB_USER_AGENT | No | Browser-like User-Agent required for the upstream WAF. The default is a valid Chrome UA string. | |
| NBB_API_TIMEOUT | No | Per-request timeout in seconds. | 30 |
| NBB_API_BASE_URL | No | SDMX REST base URL. | https://nsidisseminate-stat.nbb.be/rest |
| NBB_RETRY_ATTEMPTS | No | Number of attempts on transient errors; must be >= 1. | 3 |
| NBB_RETRY_WAIT_MAX | No | Maximum backoff delay in seconds. | 30.0 |
| NBB_HTTP_CACHE_PATH | No | Override cache location. Defaults to platformdirs.user_cache_dir. | |
| NBB_RATE_LIMIT_PERIOD | No | Rate limit window in seconds. | 60 |
| NBB_HTTP_CACHE_ENABLED | No | Enable or disable the persistent disk cache. | true |
| NBB_RETRY_WAIT_INITIAL | No | First backoff delay in seconds. | 1.0 |
| NBB_RATE_LIMIT_REQUESTS | No | Self-imposed rate limit in requests per period. | 100 |
| NBB_MEMORY_CACHE_TTL_DATA | No | TTL in seconds for data responses. | 300 |
| NBB_MEMORY_CACHE_TTL_STRUCTURE | No | TTL in seconds for structure responses. | 3600 |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
Access the National Bank of Belgium statistical API (SDMX). Use nbb_search to discover dataflows, nbb_describe to inspect a flow's dimensions, and nbb_query or nbb_quick to fetch data. Prefer nbb_quick for common topics (exchange rates, inflation, GDP, unemployment, public debt) — it routes to the right dataflow and headline series automatically. Use nbb_compare to align 2-5 series on a common time index. Errors carry a [CODE] and a 'details' JSON listing valid dimensions/codes — use them to fix the call.
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
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| nbb_searchA | Fuzzy search across the local catalogue of NBB dataflows (no API call). Filters by category and agency. Returns ranked hits with dimensions, available frequencies, time coverage and example queries. |
| nbb_describeB | Return the full enriched fiche for a dataflow (dimensions with the codes that actually hold data, multilingual names, frequencies, time coverage, common queries). Reads from the local catalogue by default; pass force_refresh=True to revalidate the structure against the live API. |
| nbb_queryA | Generic SDMX data fetch. Specify either 'key' (raw SDMX, e.g. 'D.USD') or 'filters' ({'FREQ':'D','EXR_CURRENCY':'USD'}; a list value means OR). Supports start_period, end_period, last/first_n_observations (per series). max_observations caps returned rows and max_series caps per-series stats to keep the response within the model's context budget. |
| nbb_quickA | Topic-based shortcut for common queries (exchange_rate, inflation_hicp, gdp, unemployment_rate, government_debt, policy_rate, mortgage_rate, consumer_confidence, trade_balance, …). Routes to the right dataflow and headline series. 'frequency' (A/S/Q/M/D) applies to every topic; 'currency' only to exchange_rate, e.g. nbb_quick('exchange_rate', currency='USD'). |
| nbb_compareA | Align 2-5 SDMX series on a common time index. Each series is specified as {dataflow_id, agency?, key? | filters?, label?} and must resolve to a single series. Downsamples finer frequencies to the coarsest using closing (last-of-period) aggregation. |
| nbb_statusA | Diagnostic snapshot: catalogue stats, HTTP cache footprint, API config and usage. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| NBB Catalog | Summary of the NBB dataflows organised by category. |
TDQS
Scored across 6 tools
Each tool has a distinct role: nbb_status is diagnostics, nbb_search/nbb_describe are discovery layers, nbb_query is generic fetch, nbb_quick is a topic shortcut, and nbb_compare is alignment. The main overlap is nbb_quick vs nbb_query (quick routes to predefined dataflows), but descriptions make the boundary clear enough for an agent to choose correctly.
All six tools follow a uniform nbb_<verb/noun> snake_case pattern with single-word suffixes. No mixing of styles or casing conventions.
Six tools is well-scoped for an SDMX data-access server: discovery, description, generic query, quick query, comparison, and diagnostics. Each earns its place without redundancy.
The surface covers the full workflow: search → describe → query/quick → compare, plus status diagnostics. Minor gap: no explicit tool to enumerate categories/agencies or browse all dataflows, though nbb_search filters likely suffice as a workaround.