Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault

No arguments

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

CapabilityDetails
tools
{
  "listChanged": false
}
prompts
{
  "listChanged": false
}
resources
{
  "listChanged": false
}

Tools

Functions exposed to the LLM to take actions

NameDescription
get_tool_helpA

Describe one tool visible on this facade, including its exact contract, or return a bounded workflow overview for one supported topic.

get_catalogA

Discover data packs or geometry families progressively: lite selection, full metric/query inventory, or a raw catalog download URL. Choose one result and call get_pack next.

get_packA

Inspect one selected data pack or geometry family progressively: lite starter contract, full MCP query metadata, or a raw metadata download URL. Use its next_step to retrieve data or call the preferred geometry tool.

get_eventA

Retrieve one exact disaster event and explicitly requested relationships, affected places, native observations, or geometry. Use get_data to obtain the stable event_id first.

resolve_pointA

Compact first-pass reverse geocoding for one WGS84 coordinate or a bounded point array. Returns administrative loc_id chains through Admin 3 without opening deep partitions or side-family shape banks. Use a returned shallow loc_id with resolve_deep_point for Admin 4-6 or one explicit family. Single and bulk requests share this contract; access limits are based on point count.

resolve_deep_pointA

Second-pass resolution for one WGS84 coordinate or a bounded point array. Supply one shared shallow_loc_id returned by resolve_point and one canonical family from get_catalog(catalog='geometry'). family defaults to administrative; shape-backed families use direct bbox-to-exact-shape lookup without crosswalks. Single and bulk requests share this scoped contract.

get_loc_id_infoA

Known-place navigation and enrichment tool: use only when you already have one canonical loc_id or a bounded loc_ids array. It returns identity, strict stored parentage, lifecycle, shape status, and place-specific data-pack and geometry-family availability with executable next calls. It does not list the global catalog and does not return polygon coordinates; use get_catalog to browse everything or get_geometry for shapes. Set include_hierarchy for same-release ancestors and include_references for maintained external or cross-family connections. Historical records are never replaced automatically. No payment required.

identify_dataset_geographyA

Multi-column dataset classifier: use when you do not yet know which column or latitude/longitude pair represents geography. Pass bounded samples from several named scalar columns; it selects the plausible geography column(s), then proposes a country, level, and maintained reference-system binding. It does not validate a preselected identifier column value-by-value; after selecting a code column, use identify_reference_system when explicit verification is needed. Returns up to three reviewable bindings and recommends only an unambiguous high-confidence result. No geometry is loaded and no full dataset is retained. No payment required.

identify_reference_systemA

Single-column code-system classifier: use after an identifier column has already been selected, or to inspect one bounded set of like geography codes. Pass only identifier strings from that one field so leading zeros are preserved. It determines or verifies the system, country, level, vintage, and compatible geometry bank; it does not choose among dataset columns, convert the full dataset, or return polygons. Use identify_dataset_geography instead when column selection is still unknown. Ambiguous results remain unselected until the caller retries with expected.system; a known system can be verified by supplying expected on the first call. No payment required.

convert_referenceA

The single geographic reference converter. Converts one reference, or a bounded list, through DaedalMap loc_id: X -> loc_id -> Y. Omit to_system to enter the loc_id universe; provide it for any-to-any conversion. Use get_pack first when the family or country-specific system is unknown. No payment required.

compare_geographiesA

Compare two geographic identities for the public guarantees implemented today: containment/common ancestry and temporal validity for the requested vintages. The response may include additional maintained evidence, but callers must not rely on deeper topology or relationship semantics as a stable contract until that review is complete. Use convert_reference first for names or outside identifiers. No payment required.

get_geometryA

Shape availability and bounded coordinate retrieval only: use when you already have exact loc_ids, or one administrative parent_loc_id plus target admin_level. The default fast preflight returns has_shape, shape metadata, centroid, and bounding box; set include_polygon=true only for GeoJSON coordinates. Use get_loc_id_info for hierarchy, identity, catalog coverage, or crosswalk facts; get_geometry does not return those place details. Administrative scope queries stay within the optimized Admin Spine layout, while independent geometry families require exact loc_ids. Historical geometry is returned first and successors are never substituted automatically. No payment required.

get_dataA

Retrieve rows from one selected published data pack using exact metrics, loc_id-based region filters, time/metric filters, sorting, and a row limit. Disaster event rows include stable event_id values for get_event drill-down. A parent administrative loc_id selects matching descendant rows at the pack's published grain. Call get_pack first; geometry families use their focused next-step tools.

Prompts

Interactive templates invoked by user choice

NameDescription
largest_earthquake_in_rangeStarter prompt for finding the largest earthquake in a time range, optionally scoped to a loc_id region.
count_disaster_eventsStarter prompt for counting earthquakes, volcanoes, tsunamis, or hurricanes in a time range with optional threshold and loc_id filtering.
fx_history_for_countryStarter prompt for fetching USD-normalized FX history for one or more countries at daily, weekly, or monthly granularity.

Resources

Contextual data attached and managed by the client

NameDescription
DaedalMap catalogThe live list of agent-ready DaedalMap data packs (same as get_catalog).

TDQS

A4.5/5.0

Scored across 13 tools

Disambiguation5/5

Every tool targets a clearly distinct action and data type: catalog exploration, pack inspection, place info, geometry retrieval, point resolution, identity conversion, event drill-down, and two different classifier modes. Descriptions explicitly cross-reference when to use other tools, reducing overlap confusion.

Naming Consistency5/5

All names follow a predictable lowercase snake_case pattern with a leading verb: get_* for retrievals, identify_* for classification, resolve_* for geocoding, plus convert/compare for specific operations. The verb-prefix convention makes the tool family immediately understandable.

Tool Count5/5

Thirteen tools is well within the 3-15 sweet spot and matches the breadth of the geospatial domain: catalog discovery, pack access, geometry, reference conversion, point resolution, and event lookup all earn their place without feeling bloated.

Completeness5/5

The tool set covers the full read-only workflow for a geographic data platform: discover, inspect, retrieve data and geometry, resolve points, classify and verify identifiers, convert references, compare geographies, and drill into events. No obvious dead ends or missing operations for the apparent domain.

Maintenance

ActivityActive
ResponsivenessNo issues