Entur OpenTripPlanner MCP (proof of concept)
Entur publishes, in its own GitHub org, a Java/Spring AI MCP server described as a "poc mcp using journey-planner and geocoder apis". It wraps the Journey Planner v3 (OpenTripPlanner transmodel GraphQL), the Geocoder and the Mobility v2 GraphQL APIs, and ships embedded MCP App UIs (departure board, trip map, nearby stops/mobility maps). The README documents running it as a stateless HTTP server at http://localhost:8080/mcp. The repo's Helm values name hosted ingresses (opentripplanner-mcp.entur.io for prd, opentripplanner-mcp.staging.entur.io for tst); both answered 403 Forbidden to an unauthenticated MCP initialize POST on 2026-10-09, so the hosted endpoint is not publicly reachable.
One-click install for Cursor, VS Code, Claude, and 20+ other MCP clients, powered by API Commons MCP Install — visit install.apicommons.org for more information.
Endpoint
Hosted endpoint · transport
Connect
This is a remote MCP server — point an MCP client at the endpoint URL. Clients with native remote support (Claude, Cursor, VS Code, …):
For stdio-only clients (older Claude Desktop, etc.), bridge with mcp-remote:
If the server requires authentication, add the provider's token/header (e.g. an X-API-Key) per its docs. A quick reachability check:
Tools
trip— Find trip options between two locations, with an interactive map UI.departures— Real-time departures from a stop or station, with a departure board UI.nearby-stops— Find public transport stops near a location, sorted by distance, with a map UI.alerts— Active service disruptions and cancellations.geocode— Search for locations by name or address.nearby-mobility— Defined in src/main/java/org/entur/mcp/tools/MobilityTool.java (not listed in the README tool section).poll-departures— Refreshes departure data for the departure board UI.poll-trip— Re-plans a trip with updated parameters for the trip map UI.
About MCP
The Model Context Protocol (MCP) is an open protocol Anthropic introduced for connecting LLM-based agents to external tools and data sources. Providers publish MCP servers that expose their API surface as structured, discoverable tools — an MCP-compatible client (Claude Desktop, Cursor, Cline, Continue, etc.) can connect to the server and call its tools without any per-provider integration code.
Browse every MCP server on the APIs.io network or compare with the broader Agent Skill surfaces of the same providers.
Work with this as data
Every MCP server here is available over the APIs.io API and to AI agents over MCP.