InfraNode
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| INFRANODE_REDIS_URL | No | The Redis connection URL. Can be adjusted if using a non-default Redis instance. | redis://localhost:6379/0 |
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_cityA | Get base data for a German city (population, area, coordinates). Sourced from Wikidata. Read-only. Useful as a first lookup to confirm a city
exists and get its core attributes. For a broader question about the city
(what data is available at all) use |
| get_city_overviewA | Get a ONE-CALL overview of everything InfraNode knows about a German city. Start here for any city question. Returns: the city's base data, a CATALOG of
all 67 available data types (weather, air quality, public transit, trains,
traffic, charging, parking, solar, energy, demographics, taxes, accidents,
tourism, heritage, trees, population density, playgrounds, post boxes and many
more), each with its coverage status and the exact tool to call next (for most
data types that is |
| get_city_resourceA | Fetch ANY per-city data type by its key (generic accessor, 67 data types). One tool for the whole breadth of InfraNode: live data (air, traffic, transit
stops, parking, charging, water-level, flood, sharing, fuel-prices, icu-live,
webcams, station-departures/-arrivals/stations, ...), statistics
(demographics, unemployment, tourism, accidents, crime-stats, indicators,
land-values, tax-rates, insolvencies, ...), infrastructure and environment
(solar, solar-roofs, district-heating, energy, heritage, tree-cadastre,
playgrounds, public-toilets, markets, education, ...) and more. Discover the
valid keys and per-city coverage with |
| air_qualityA | Get official air quality for a German city (PM10, NO2 and more). Sourced from the Umweltbundesamt (UBA). Read-only. For live nearest-station
hourly readings use |
| weatherA | Get current weather observations for a German city. Sourced from the Deutscher Wetterdienst (DWD): temperature, wind,
precipitation and related fields. Read-only, current conditions only (not a
forecast). For warnings use |
| poisA | Get points of interest in a German city, filtered by type. Sourced from OpenStreetMap. Read-only. |
| station_board_departuresA | Get live departures for ANY railway station by its EVA number. Covers all train categories including local/regional (S/RB/RE) and long
distance, with real-time delays, cancellations and disruption messages. Get
the EVA from |
| station_board_arrivalsA | Get live arrivals for ANY railway station by its EVA number. Mirror of |
| transit_departuresA | Get live public-transport departures with real-time delays for a stop. Sourced from GTFS-RT/HVV/VGN. Unlike the static stop list
( |
| list_citiesA | List all covered cities (slug, federal state, population, coverage). Takes no arguments. Call this first to discover valid city slugs before invoking any city-scoped tool. Read-only. |
| sourcesA | List all data sources with license, attribution and availability. Takes no arguments. Shows which upstream sources InfraNode bundles and whether each is currently active. Read-only. |
| compareA | Compare ONE resource across MULTIPLE cities in a single response. Fans the resource out over the listed cities and returns a per-city
|
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| city_overview | Get a complete picture of a German city and what InfraNode offers for it. |
| city_briefing | A concise live briefing (weather, air, transit) for a German city. |
| compare_air_quality | Compare current air quality across several German cities. |
| commute_check | Check the live commute/transit situation for a German city. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| cities_resource | All covered German cities with slug, federal state, population and coverage. |
| sources_resource | All InfraNode data sources with license, attribution and availability. |
| catalog_resource | The catalog of all per-city data types: label, matching tool and REST path. Lets an agent browse the full breadth of InfraNode (every data type and the tool that fetches it) without a tool call. For a live, per-city view with coverage status and highlights, call get_city_overview(slug). |
TDQS
Scored across 12 tools
Most tools have distinct targets, and the generic get_city_resource is clearly positioned as the fallback for many resource types. Intentional overlap exists between get_city/get_city_overview and air_quality vs resource='air', but the descriptions explicitly route agents to the correct tool. Station board and transit departures are also disambiguated by mode and ID type.
Names are readable and consistently snake_case, but the style is mixed: get_city/get_city_resource use verb_noun, while air_quality/weather/pois/sources are bare nouns and station_board_departures/transit_departures use noun_noun patterns. No single clear convention exists, though the get_city_* family provides some structure.
12 tools is well within the ideal range and each one supports a distinct workflow: discovery, single-city lookup, resource-specific retrieval, station boards, and multi-city comparison. No redundant tools stand out, and the generic resource accessor keeps the count from ballooning despite a large underlying data catalog.
The server covers the full read-only data lifecycle: list_cities for discovery, get_city_overview for a one-call catalog, get_city_resource for any of the 67 data types, convenience tools for common slices, and compare for multi-city analysis. For its stated purpose, there are no critical dead ends.