Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
BART_API_KEYNoCustom BART developer keyMW9S-E7SL-26DU-VV8V
MBTA_API_KEYNoHigher rate limits for MBTA v3 REST API
MUNI_API_KEYNoDirect 511.org StopMonitoring live prediction feed
MARTA_API_KEYNoDirect MARTA Realtime REST API key
TRIMET_APP_IDNoDirect developer.trimet.org live arrivals feed
WMATA_API_KEYNoDirect WMATA Developer API key
FAIRFAX_API_KEYNoDirect Fairfax County Connector predictions feed
RIDE_ON_API_KEYNoDirect Montgomery County Open Data live predictions
ACTRANSIT_API_KEYNoDirect AC Transit actrealtime prediction feed
CTA_TRAIN_API_KEYNoDirect CTA Train Tracker GPS hardware feed

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
}

Tools

Functions exposed to the LLM to take actions

NameDescription
list_supported_citiesA

Lists all supported US transit cities, transit agencies, modes, and feature capabilities.

list_routesA

Lists public transit routes/lines for a supported city with optional search filtering.

get_route_stopsA

Retrieves stops and stations along a specific transit route in a supported city.

get_departuresA

Gets real-time departures, live countdown minutes, platform, delay, and status for a stop or station.

get_service_alertsB

Retrieves real-time transit service alerts, disruptions, construction advisories, and delays.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

TDQS

A3.9/5.0

Scored across 5 tools

Disambiguation5/5

Each tool targets a distinct resource: city metadata, routes, stops, real-time departures, and alerts. No overlap in purpose; agents can easily select the correct tool based on the desired information.

Naming Consistency5/5

All tools follow a consistent verb_noun snake_case pattern (list_*, get_*). Naming is predictable and uniform, making it easy to infer tool behavior from the name alone.

Tool Count5/5

With 5 tools covering the core transit use cases (city discovery, route listing, stops, departures, alerts), the set is well-scoped and neither sparse nor bloated. Each tool contributes a distinct piece of the domain.

Completeness4/5

The tool set covers the main journey of exploring a city's transit system and retrieving real-time data. Minor gaps exist, such as a dedicated stop search or route details endpoint, but agents can still accomplish typical tasks without dead ends.

Maintenance

ActivityMaintained
ResponsivenessNo issues