Agent-ready OpenAPI document · curated by JenticMaps GeolocationRouting DirectionsapiKey24 EndpointsREST
Know of an official OpenAPI document? Contribute it →
For Agents
Get real-time and scheduled MBTA transit data for Boston subway, bus, commuter rail, and ferry - including predictions, alerts, and vehicle positions.
Use for: I need to find when the next train arrives at a stop, Get current service alerts for the Red Line, Retrieve all bus stops within walking distance of an address, Check whether an elevator is working at North Station
Not supported: Does not handle fare payment, ticketing, or driving directions - use for MBTA transit data, predictions, alerts, and vehicle tracking only.
Jentic publishes the only available OpenAPI specification for MBTA V3 API, keeping it validated and agent-ready. The MBTA V3 API exposes real-time and scheduled transit data for the Massachusetts Bay Transportation Authority covering subway, commuter rail, bus, and ferry services across Greater Boston. It follows the JSON:API specification and includes 24 endpoints for stops, routes, schedules, predictions, vehicles, alerts, facilities, and trip planning data. Agents use it for arrival predictions, service alerts, and accessibility-aware journey planning.
Install Jentic One Beta
Connect the MBTA V3 API to your agent
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the MBTA V3 API, or any other public or private API you need. You set the rules, the agent never sees your credentials, and every call is logged.
Two steps, two machines. Install the instance in a safe environment, then register your agent from wherever it runs.
1
Step 1: Jentic One Host machine
# On the machine that will host your Jentic One instance:
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Fmbta.com%2Fmbta" | sh2
Step 2: Agent machine
# On the machine where your agent runs (keep this separate from the instance):
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Fmbta.com%2Fmbta" | sh
jentic register # connects your agent to your Jentic One instanceJentic One is in public beta. The setup above keeps your agent separate from the instance, which is what you want before using real credentials: an agent running as the same OS user as Jentic One can read its stored keys directly. Just evaluating? A single local install is fine to start. See the secure deployment guide for the tiers.
Capabilities
What an agent can do with MBTA V3 API.
Retrieve real-time arrival predictions for any MBTA stop
Pull current vehicle positions for buses, trains, and ferries
List active service alerts affecting routes, stops, or trips
Look up scheduled trips and stop-time tables for a route
Surface elevator and escalator status from facility data
Fetch route shapes and geometry for map rendering
Resolve stop and station metadata including accessibility flags
Use Cases
Patterns agents use MBTA V3 API for, with concrete tasks.
★ Real-Time Arrival Display
Show next-bus and next-train countdowns on a kiosk, signage screen, or chat interface using MBTA prediction data. The /predictions endpoint returns upcoming arrivals filtered by stop, route, or trip, with departure timestamps and direction. Agents typically poll every 15-30 seconds and render the soonest two or three arrivals per direction.
Call GET /predictions filtered by stop=place-pktrm and direction_id=0, then return the next three arrival times grouped by route.
Service Alert Monitoring
Watch for new MBTA service alerts that affect a defined set of routes or stops and notify riders through Slack, email, or a status page. The /alerts endpoint returns currently active alerts with severity, lifecycle, affected services, and human-readable descriptions. Agents diff the response against the previous poll and post only newly-active or newly-cleared entries.
Call GET /alerts filtered by route=Red and lifecycle=NEW, then post any results to a Slack channel as a formatted message including the alert header and effect.
Accessibility-Aware Trip Planning
Help riders with mobility needs avoid stations with broken elevators by combining /facilities and /live_facilities responses with /stops. Agents read the live facility status, filter stops where elevators are out of service, and recommend alternate stations or routes. This is increasingly important for MBTA's accessibility commitments and rider experience.
Call GET /live_facilities, filter to facilities with current_status=OUT_OF_ORDER and type=ELEVATOR, then return the affected stop ids.
AI Agent for Daily Commuter Briefings
Build an agent that, each weekday morning, queries MBTA predictions and alerts for a commuter's stops and routes, then sends a tailored briefing to their phone. The agent searches Jentic for 'check MBTA service status', loads the alerts and predictions schemas, and executes calls scoped to the user's saved routes. The output is a one-paragraph briefing answering 'should I leave now?' without the user opening multiple transit apps.
For routes Red and 1 from stop place-cntsq, call GET /alerts and GET /predictions, then return a paragraph summarising any active alerts plus the next two arrival times for each route.
Key Endpoints
24 endpoints — jentic publishes the only available openapi specification for mbta v3 api, keeping it validated and agent-ready.
METHOD
PATH
DESCRIPTION
GET
/predictions
Real-time arrival predictions
GET
/alerts
Active service alerts
GET
/routes
List MBTA routes
GET
/stops
List stops and stations
GET
/vehicles
Live vehicle positions
GET
/schedules
Scheduled trips and stop times
GET
/live_facilities
Current facility status
GET
/lines
Logical transit lines grouping routes
GET
/predictions
Real-time arrival predictions
GET
/alerts
Active service alerts
GET
/routes
List MBTA routes
GET
/stops
List stops and stations
GET
/vehicles
Live vehicle positions
GET
/schedules
Scheduled trips and stop times
GET
/live_facilities
Current facility status
GET
/lines
Logical transit lines grouping routes
Jentic AI Readiness Score
This API is usable in Jentic One now. Its AI-readiness score against Jentic's framework shows where it stands today and where improvements would make it even easier for agents to use.
M
MBTA V3 API
- AI-Aware (B-)62/100
87
Foundational Compliance63
Developer Experience & Jentic Compatibility53
AI-Readiness & Agent Experience94
Agent Usability33
Security100
AI DiscoverabilityPowered by JenticScoring Framework 1.0.0 | Scoring Engine 0.4.0
Show dimension breakdown
87
Foundational Compliance
Base layer of spec validity and structural soundness.
Grade: ASignals: 4
97%
Lint Results
Aggregated quality score from linter diagnostics, weighted by severity.
100%
Resolution Completeness
Percentage of `$ref` references that resolve successfully.
100%
Specification Validity
Checks whether the API description parses successfully and conforms to its declared specification (e.g., OpenAPI).
50%
Structural Integrity
Structural correctness score based on schema issues using logarithmic dampening.
63
Developer Experience & Jentic Compatibility
Clarity, completeness, and ingestion readiness for developers and tooling.
Grade: B-Signals: 4
0%
Example Density
How richly the API is illustrated with examples.
100%
Example Validity
Percentage of examples that conform to their schemas.
50%
Response Coverage
Percentage of operations with complete response definitions (success, client error, server error).
100%
Tooling Readiness
Health of API ingestion, bundling, and resolution within Jentic pipelines.
53
AI-Readiness & Agent Experience
Semantic breadth, depth, and agent comprehension for AI systems.
Grade: C-Signals: 4
61%
Description Coverage
Coverage of descriptions across API elements.
0%
Error Standardization
Coverage of RFC 9457 Problem Details for error responses.
100%
OperationId Quality
Coverage, uniqueness, and casing consistency of operationIds for AI inference.
50%
Summary Coverage
Coverage of summaries across operations/tags/info.
94
Agent Usability
Functional utility, complexity comfort, and AI orchestration readiness.
Grade: A+Signals: 1
94%
Complexity Comfort
Agent comfort level based on API operational and structural complexity.
33
Security
Trust, risk posture, and security compliance.
Grade: FSignals: 1
33%
Authentication Strength
Average quality of security schemes based on authentication method strength (weakest link for OAuth2).
100
AI Discoverability
Findability, semantic richness, and reasoning readiness.
Grade: A+Signals: 1
100%
Descriptive Richness
Clarity and depth of descriptions across API elements.
Score it yourself
Every API in the directory is allowlisted, so you can re-score it with no key required.
npx @jentic/api-scorecard-cli score <openapi-url>Why Jentic?
What agents get from Jentic-routed access to this vendor.
Setup
Wiring the MBTA V3 API by hand means sending your key in the x-api-key header, pointing at the api-v3.mbta.com host, and parsing its JSON:API responses yourself. Through Jentic you install once, import the MBTA V3 API from the API Directory, store the key once, and your agent calls it.
Permission scoping
MBTA queries filter transit data through query parameters rather than resource ids in the URL path, so you limit the agent to the operations it needs, such as fetching predictions, alerts, or vehicle positions. It calls only the operations you allow, and since this surface is read-only, it retrieves transit data without any write access.
Credential isolation
Your MBTA API key is stored once, encrypted, by your own Jentic One instance and attached to the x-api-key header at execution time. It never enters the agent's prompt, logs, or context.
Intent-based discovery
Agents search Jentic by intent such as 'get MBTA arrival predictions for a stop', and Jentic returns the matching MBTA operation with its input schema so the agent calls the right endpoint without parsing the JSON:API documentation.
Related APIs
Alternatives and complements available in the Jentic catalogue.
FAQs
Specific to using MBTA V3 API through Jentic.
Why is there no official OpenAPI spec for MBTA V3 API?
MBTA does not publish an OpenAPI specification. Jentic generates and maintains this spec so that AI agents and developers can call MBTA V3 API via structured tooling. It is validated against the live API and kept up to date. Get started with Jentic One, the self-hosted execution layer.
What authentication does the MBTA V3 API use?
MBTA accepts an API key either as a query parameter (api_key) or in the x-api-key header. Anonymous calls work but with much stricter rate limits. Through Jentic, the key is stored encrypted in your Jentic One instance and injected as a header at execution time, so the raw key never enters the agent's transcript.
Can I get real-time vehicle positions with the MBTA API?
Yes. GET /vehicles returns live vehicle positions, including latitude, longitude, current status, and bearing, filterable by route or trip. Combined with /predictions, this is the standard data source for arrival countdown displays and live route maps.
What are the rate limits for the MBTA V3 API?
Anonymous usage is capped at around 20 requests per minute; authenticated keys are typically allowed 1,000 requests per minute. The exact limits and how to request a higher tier are documented at api-v3.mbta.com. Responses use 429 status codes when limits are exceeded.
How do I get arrival predictions through Jentic?
Search Jentic for 'get MBTA arrival predictions for a stop', load the schema for GET /predictions, and execute with filter[stop]=place-pktrm. Jentic attaches the API-key header automatically and returns predictions sorted by arrival time.
Does the MBTA API include accessibility data?
Yes. GET /facilities returns elevators, escalators, and parking facilities with type and properties, and GET /live_facilities returns current operational status. Together these let agents build accessibility-aware journey suggestions that route riders around out-of-order elevators.
Does the MBTA API follow the JSON:API specification?
Yes. Responses follow the JSON:API spec with data, attributes, relationships, and included sections, and requests support sparse fieldsets, includes, and filters. This makes it well-suited to single-call composite responses, but agents need to parse the JSON:API envelope rather than expecting flat objects.
Can I limit what my agent is allowed to do with the MBTA V3 API?
Yes. Because you run Jentic One yourself, your own rules decide which MBTA operations and credentials the agent can use, so you can allow just the calls it needs, such as GET /predictions, GET /alerts, or GET /vehicles, and withhold the rest. MBTA filters transit data through query parameters rather than resource ids in the URL path, so scoping happens at the operation level and the agent only ever calls the operations you permit. Since this surface is entirely read-only, the agent retrieves transit data with no write access at all.
GET STARTED