Skip to main content
Glama
openfantasymap

odh-mcp-server

by openfantasymap
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Hybrid

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
ODH_TIMEOUTNoTimeout in seconds for ODH API requests.10
ODH_BASE_URLNoBase URL for the Open Data Hub API.https://tourism.api.opendatahub.com/v1
DEFAULT_WORLDNoThe default world to load on startup.earth-313
NOMINATIM_URLNoBase URL for Nominatim geocoding service.https://nominatim.openstreetmap.org
NOMINATIM_USER_AGENTNoUser-Agent header for Nominatim requests.odh-mcp-server/0.1 (opensource hospitality MCP)

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": true
}
logging
{}
prompts
{
  "listChanged": false
}
resources
{
  "subscribe": false,
  "listChanged": false
}
extensions
{
  "io.modelcontextprotocol/ui": {}
}
experimental
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
set_worldA

Set the current world context for all subsequent queries.

Available worlds:

  • earth-313: South Tyrol / Alto Adige, Italy. Real hospitality data from the Open Data Hub.

  • Any OFM world ID (e.g. 'bral'): fixture-backed fantasy worlds from the OpenFantasyMap project.

Returns a confirmation message with the world's description and available tools.

describe_worldA

Return a narrative description of the current world, including what data is available and how to query it.

find_accommodationsA

Find accommodations in the current world.

Parameters:

  • near: place name (geocoded automatically for earth-313, landmark-resolved for other worlds)

  • lat/lon: alternative to near, direct coordinates

  • radius_m: search radius in meters / units (default 5000)

  • features: list of desired features. For earth-313: family, pool, sauna, parking, wifi, accessible, pets, meeting, pickup, allergy For bral: spacefarer-friendly, private-rooms, common-room, stabling, secure-storage, pets

  • category: star rating for earth-313 (1star to 5stars), ignored for bral

  • available_from/available_to: date range (yyyy-MM-dd), earth-313 only

  • max_results: maximum number of results (default 5)

Returns a formatted narrative list of accommodations with key details.

find_eventsA

Find events in the current world.

Parameters:

  • near: place name (geocoded for earth-313, landmark-resolved for bral)

  • lat/lon: direct coordinates, alternative to near

  • radius_m: search radius in meters / units (default 10000)

  • date_from/date_to: date range filter (yyyy-MM-dd), primarily for earth-313

  • topic: topic or category keyword (e.g. "music", "sport", "culture", "market")

  • max_results: maximum number of results (default 5)

Returns a formatted narrative list of events.

find_gastronomyA

Find restaurants, food stalls, and gastronomy places in the current world.

Parameters:

  • near: place name (geocoded for earth-313, landmark-resolved for bral)

  • lat/lon: direct coordinates, alternative to near

  • radius_m: search radius in meters / units (default 5000)

  • cuisine: cuisine type keyword (e.g. "italian", "shou", "bakery", "tavern")

  • features: desired features (e.g. ["vegetarian-options", "outdoor-seating"])

  • max_results: maximum number of results (default 5)

Returns a formatted narrative list of gastronomy places.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A4.4/5.0

Scored across 5 tools

Disambiguation5/5

Each tool targets a distinct operation: set_world establishes context, describe_world explains it, and the three find_* tools query for accommodations, events, and gastronomy separately. Even though they share parameters like near and radius_m, the entity types are clearly different, so an agent can easily select the right tool.

Naming Consistency5/5

All tool names follow a consistent verb_noun pattern in snake_case: set_world, describe_world, find_accommodations, find_events, find_gastronomy. The verbs (set, describe, find) are clear and the nouns are specific, making the pattern predictable.

Tool Count5/5

With 5 tools, the server is well-scoped for its purpose of exploring hospitality and tourism data in a world context. Each tool earns its place: world management (set, describe) and three distinct search types (accommodation, events, gastronomy). No redundancy or bloat.

Completeness5/5

The server's domain is read-only exploration of world-based hospitality data, and it covers the core workflow: set the world to establish context, understand what data is available via describe_world, and then search for the three primary POI types. There are no obvious dead ends, and all CRUD operations beyond reading are outside the stated purpose.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources