Real-time MBTA transit data (Boston) exposed through a Model Context Protocol (M
Real-time MBTA transit data (Boston) exposed through a Model Context Protocol (MCP) server, built with Python and Streamable HTTP and deployed on Google Cloud Run.
active Production-safe Score 75/100 http no auth
At a glance
| Endpoint | https://mbta.metaverseprofessional.tech/mcp |
|---|---|
| Source | https://github.com/jegamboafuentes/MBTA-MCP |
| Transport | http |
| Tools | 6 |
| Auth | none |
| First seen | 2026-08-18 22:17:39 |
| Last checked | 2026-11-17 07:19:07 |
Observed reliability
| 7-day uptime | 100% |
|---|---|
| 24-hour uptime | 100% |
| Handshake success | 100% |
| Latency p50 / p95 | 5572 / 6997 ms |
| Last successful check | 2026-11-17 07:19:07 |
Measured by Arclan's validator via repeated live MCP handshakes. How this is computed →
Tools (6)
get_routes— List MBTA routes. Use this first when you need route IDs or want to browse the system. Optionally filter by GTFS route type: 0=lighget_stops_for_route— List stops served by a specific MBTA route. Use when you already know a route ID (for example Red, Orange, Green-B, or 1) and needfind_stop— Find stops by name or partial name. Use when a rider mentions a station or stop (for example "Park Street" or "South Station") andget_next_arrivals— Get upcoming predicted arrivals/departures for a stop. Requires a stop ID from find_stop or get_stops_for_route. Optionally filterget_alerts— Get MBTA service alerts and disruptions. Use for delays, detours, elevator outages, and service changes. Optionally filter by routeget_vehicles— Get live vehicle locations and status. Use when the rider asks where trains/buses are right now. Optionally filter by route_id (rec
Validation history
| Checked | Reachable | Handshake | Latency | Score | State |
|---|---|---|---|---|---|
| 2026-11-17 07:19:07 | ✓ | ✓ | 10262 ms | 85 | active |
| 2026-11-17 05:36:07 | ✓ | ✓ | 3624 ms | 85 | active |
| 2026-11-17 04:32:02 | ✓ | ✓ | 4624 ms | 85 | active |
| 2026-11-17 02:46:23 | ✓ | ✓ | 3195 ms | 85 | active |
| 2026-11-17 01:36:22 | ✓ | ✓ | 3555 ms | 85 | active |
| 2026-11-16 10:26:59 | ✓ | ✓ | 3607 ms | 85 | active |
| 2026-11-16 10:06:00 | ✓ | ✓ | 3675 ms | 85 | active |
| 2026-11-16 09:48:18 | ✓ | ✓ | 3472 ms | 85 | active |
| 2026-11-16 09:31:02 | ✓ | ✓ | 5470 ms | 85 | active |
| 2026-11-16 07:30:47 | ✓ | ✓ | 5146 ms | 85 | active |
| 2026-11-16 05:30:32 | ✓ | ✓ | 5242 ms | 85 | active |
| 2026-11-16 03:30:24 | ✓ | ✓ | 5129 ms | 85 | active |
| 2026-11-16 01:30:13 | ✓ | ✓ | 3514 ms | 85 | active |
| 2026-11-15 23:29:54 | ✓ | ✓ | 323 ms | 89 | active |
| 2026-11-15 21:29:52 | ✓ | ✓ | 3418 ms | 85 | active |
Query this programmatically
Agents can pull this record live over the MCP protocol or REST:
get_server("https://mbta.metaverseprofessional.tech/mcp") # via the Arclan MCP endpoint https://arclan.ai/mcp
GET https://arclan.ai/api/registry/mbta-metaverseprofessional-tech-mcp # JSON