apibase

MBTA Stops & Stations

mbta.transit.stops

Read-onlyIdempotent

Find Boston MBTA stops and stations — filter by route ID or by geographic coordinates + radius. Returns stop ID, name, latitude/longitude, municipality, vehicle type, platform info, and wheelchair boarding status. Stop IDs returned here are used as filter inputs for mbta-transit.alerts and mbta-transit.predictions. Use location_type=1 to return only major stations (parent stops); location_type=0 for individual platforms. Example: route="Red" returns all 22 Red Line stops from Alewife to Braintree/Ashmont. MassDOT Open Data License, no upstream cost.

Input Schema

TableJSON Schema

Name	Required	Description
`limit`	No	Maximum number of stops to return (default 25, max 100)
`route`	No	Filter stops by route ID (e.g. "Red" for Red Line, "1" for Route 1 bus, "CR-Fairmount" for commuter rail). Use mbta-transit.routes to get route IDs.
`radius`	No	Search radius in degrees around lat/lon (approx 0.01° ≈ 1 km). Use with latitude+longitude.
`latitude`	No	Center latitude for proximity search. Must be paired with longitude and radius (e.g. 42.3601 for Boston)
`longitude`	No	Center longitude for proximity search. Must be paired with latitude and radius (e.g. -71.0589 for Boston)
`location_type`	No	Filter by location type: 0=individual stop/platform, 1=station (parent), 2=station entrance/exit

Output Schema

TableJSON Schema

Name	Required	Description	Default
`error`	No	Present only when the call failed. Includes error code, message, request_id, and any provider-specific extras.
`result`	No	Tool response payload. Shape varies per tool — consult the tool description and inputSchema. May be an object, array, string, or number depending on the upstream provider response.

Schema Changelog

Changes observed during successful MCP inspections.

First observedSep 22, 2026

TDQS

A4.6/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already establish that this is read-only, idempotent, and non-destructive, so the description's extra behavioral detail is valuable rather than redundant. It enumerates returned fields, explains parent-station vs platform filtering via location_type, and gives a concrete route='Red' example with expected line coverage. No contradiction with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well front-loaded with purpose and main filter modes, and it remains compact given six parameters and two search modes. However, the license/cost sentence is tangential to invocation, and some location_type details duplicate the schema, so slightly more trimming was possible.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With all parameters optional, an output schema present, and annotations covering safety, the description covers the main invocation paths, output fields, cross-tool relationships, and a concrete example. An agent has everything needed to decide when to call this tool and how to use it correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is high and the schema already documents every parameter. The description adds useful framing by presenting route and coordinates+radius as alternative search modes, clarifying location_type's role, and giving a concrete Red Line example, though some of this repeats schema-level descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb and resource: 'Find Boston MBTA stops and stations.' It immediately states the two main filter modes (route ID or geographic coordinates + radius) and lists exactly what is returned. It also distinguishes the tool from its MBTA siblings by noting that returned stop IDs feed mbta-transit.alerts and mbta-transit.predictions.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives clear usage context: filter by route or by coordinates+radius, use location_type to choose station vs platform granularity, and consult mbta-transit.routes to obtain route IDs. The only blemish is that sibling tool references use hyphens ('mbta-transit.routes') rather than the dot-separated names in the tool list, which could cause a minor lookup mismatch for an agent.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All apibase tools Inspect

Try in Browser

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

Glama MCP Gateway

Add one secure layer between your agents and this server.