Skip to main content
Glama
Sign In
odpt-mcp

odpt-mcp

by koizumikento
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

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
{
  "subscribe": false,
  "listChanged": false
}

Tools

Functions exposed to the LLM to take actions

NameDescription
search_railwayB

Find stations or railway lines operated by Toei, by Japanese or English name.

get_station_timetableA

Get scheduled Toei rail departures by station ID from search_railway.

Filter by full ODPT calendar and rail direction IDs. Departures retain
the provider's service-day order within each timetable.
get_train_statusA

Get Toei rail service notices with provider timestamps and expiry.

Supply a line ID from search_railway to restrict the notices. An empty
result means the API returned no matching notices. Check valid_until
before using a notice as current information.
get_railway_fareA

Get listed Toei rail fares in yen for an exact pair of station IDs.

search_bus_stopsA

Find Toei bus stops by exact Japanese name and get their platform IDs.

get_bus_stop_timetableB

Get scheduled Toei bus departures from a stop ID returned by search_bus_stops.

available_timetables lists services with their weekday/holiday labels,
calendar IDs, and route IDs. Departures retain the provider's order.
get_bus_routeB

List stops along a Toei bus route pattern from search_bus_stops or its timetable.

get_bus_fareA

Get listed Toei bus fares in yen between two stops on the same route pattern.

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

A4/5.0

Scored across 8 tools

Disambiguation5/5

Each tool targets a distinct resource+action: search (railway/stops) vs. schedule (timetable) vs. price (fare) vs. status, cleanly partitioned between the rail and bus domains. An agent can unambiguously route a transit query to one tool, and the descriptions reinforce the IDs each downstream tool needs.

Naming Consistency5/5

All names use consistent snake_case with a verb_noun structure (search_railway, get_station_timetable, get_bus_fare). The domain noun (railway vs. bus) is predictable across the set, with no mixed conventions.

Tool Count5/5

Eight tools is well within the ideal range and each earns its place: a search, timetable, fare, and status tool for each of the two transit domains. Nothing is redundant or obviously missing from a count perspective.

Completeness4/5

The surface covers the core lifecycle for both rail and bus: find the entity, get its schedule, get the fare, plus rail service status. Minor gaps remain, such as resolving a line to its full station sequence or listing all stops on a rail line (the bus side has get_bus_route but the rail side lacks an equivalent).

Maintenance

ActivityMaintained
ResponsivenessOutdated data

Resources