mbta.transit.predictions
Get real-time arrival and departure predictions for Boston MBTA stops — live vehicle tracking data for subway, bus, commuter rail, and ferry. Returns predicted arrival_time, departure_time (ISO 8601), direction, status (e.g. "Boarding"), schedule relationship (SCHEDULED/SKIPPED/NO_DATA), and asso...
This record as markdown: /tools/io-github-whiteknightonhorse-apibase/mbta.transit.predictions.md
What mbta.transit.predictions does on Apibase
AI agents call mbta.transit.predictions to retrieve information from Apibase without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
stop | string | — | Stop or station ID for arrival/departure predictions (e.g. "place-sstat" for South Station, "place-pktrm" for Park Street). Use mbta-transit.stops to find stop |
limit | integer | — | Maximum number of predictions to return (default 10, max 50). Each prediction is one scheduled stop for one vehicle. |
route | string | — | Route ID to get predictions for (e.g. "Red", "Green-B", "1"). At least one of stop or route is required. |
direction_id | integer | — | Filter by direction: 0=outbound (away from downtown/terminus), 1=inbound (toward downtown/terminus). See mbta-transit.routes for direction names. |
Parameters from the server's own tool schema.
Why mbta.transit.predictions is rated Low
Tool queries public transit data without modifying state or executing external operations.
From the tool's definition Get real-time arrival and departure predictions, live vehicle tracking data, returns predicted times and IDs
Attacks that exploit this kind of access
The rule that runs mbta.transit.predictions safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Apibase, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For mbta.transit.predictions, this is the rule to start with:
mbta.transit.predictions is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Apibase, apply this rule, and every mbta.transit.predictions call is checked against it from then on.
Questions about mbta.transit.predictions
Get real-time arrival and departure predictions for Boston MBTA stops — live vehicle tracking data for subway, bus, commuter rail, and ferry. Returns predicted arrival_time, departure_time (ISO 8601), direction, status (e.g. "Boarding"), schedule relationship (SCHEDULED/SKIPPED/NO_DATA), and associated route, stop, trip, and vehicle IDs. Requires at least one filter: stop ID (e.g. "place-sstat" for South Station, "place-pktrm" for Park Street) or route ID. Use direction_id to filter inbound (1) vs outbound (0). MassDOT Open Data License, real-time live data, no upstream cost. It is categorised as a Read tool in the Apibase MCP Server, which means it retrieves data without modifying state.
mbta.transit.predictions accepts 4 parameters: stop, limit, route, direction_id. The full parameter table on this page comes from the server's own tool schema.
Register the Apibase MCP server in PolicyLayer and add a rule for mbta.transit.predictions: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Apibase. Nothing to install.
mbta.transit.predictions is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the mbta.transit.predictions rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for mbta.transit.predictions. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
mbta.transit.predictions is provided by the Apibase MCP server (apibase-mcp-client). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Apibase, and thousands of servers like it.
This server
Across the catalogue