Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
MAX_H3_CELLSNoSafety cap for H3 grid generation50000
OVERPASS_API_URLNoCustom Overpass endpoint. By default, rotates between overpass-api.de and kumi.systems.
MAPBOX_ACCESS_TOKENNoEnables natural language location search (e.g. "San Francisco")

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
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
get_boundsA

Get converted coordinates for a bounding box or text location search. Supports parsing WKT, GeoJSON, ogrinfo extent, and raw coordinate strings. If MAPBOX_ACCESS_TOKEN is not set, you MUST provide explicit coordinates via 'bbox'.

get_h3_indicesA

Get Uber H3 cell indices for a bounding box area at a target resolution. Input supports WKT, GeoJSON, ogrinfo extent, and raw coordinate strings.

generate_share_urlA

Generates a URL that links to the visual Bounding Box tool to display these coordinates on a map. Supports WKT, GeoJSON, ogrinfo extent, and raw coordinate strings as input.

search_overpassA

Execute an Overpass QL query to find POIs, roads, or other OSM features within a bounding box or radius. The server wraps your query in the appropriate spatial filter and returns structured JSON with a map link.

SEARCH MODES:

  • Bounding box (default): searches a rectangular area. Use for region/area queries ('hospitals in Manhattan', 'parks in downtown Seattle').

  • Circle: searches within an exact radius. Use ONLY when the user specifies an explicit distance ('within 2km of JFK', '500 metres from the Eiffel Tower', '1 mile from Times Square'). Omit radius_meters for vague terms like 'near' or 'close to'.

COMMON TAG EXAMPLES:

  • Restaurants: nwr["amenity"="restaurant"]

  • Pizza: nwr["amenity"="fast_food"]["cuisine"="pizza"]

  • Supermarkets: nwr["shop"="supermarket"]

  • Parks: nwr["leisure"="park"]

  • Hospitals: nwr["amenity"="hospital"]

  • Schools: nwr["amenity"="school"]

  • Parking: nwr["amenity"="parking"]

  • Highways/Roads: way["highway"]

list_osm_tagsA

Discovery tool to look up the correct OpenStreetMap tags for a given category. Helps prevent hallucinating incorrect tags before writing an Overpass query.

aggregate_overpass_h3B

Executes an Overpass query and bins the results into H3 hexagons at a specified resolution to analyze spatial density.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

TDQS

A4/5.0

Scored across 6 tools

Disambiguation5/5

Each tool has a clearly distinct purpose: coordinate conversion, Overpass querying, H3 indexing, URL generation, and tag discovery. There is no ambiguity between tools like aggregate_overpass_h3 and search_overpass due to detailed descriptions.

Naming Consistency5/5

All tool names follow the verb_noun pattern in snake_case (e.g., get_bounds, list_osm_tags, search_overpass). The naming is perfectly consistent across all six tools.

Tool Count5/5

With 6 tools, the server covers core spatial operations without being too heavy or too light. Each tool serves a necessary function for bounding box-based OSM queries and H3 analysis.

Completeness4/5

The tool set covers essential workflows: coordinate parsing, Overpass query execution, H3 analysis, tag discovery, and URL generation. Minor gaps exist, such as no tool for reverse geocoding or listing OSM categories beyond tag lookup, but the surface is largely complete for the domain.

Maintenance

ActivitySlowing
ResponsivenessNo issues