MCP servers · chelseakr

GTFS Scorecard: daily GTFS feed quality grades and fixes

Publishes dated, plain-language quality grades for GTFS transit feeds, each with three prioritized fixes and a history, aimed at small transit agencies and the people who support them.

This text was machine-translated from the publisher's own information and has not been checked by a human editor. The publisher's original text is the reference.

This resource was imported automatically from the sources listed below and has not been reviewed by the AI Gate team yet. The description is the publisher's own, as published. Check the repository before installing.

What it does

GTFS Scorecard grades GTFS transit feeds each day and publishes the result in plain language, with the three most important fixes and a reason for each. An overall grade combines correctness, freshness, rider experience completeness and, when measured, realtime quality. Correctness findings come from MobilityData's canonical validator; the project does not implement its own validator. For U.S. agencies it also gives an NTD GTFS-readiness read. Each agency receives one JSON artifact per day, forming a trend history, and an embeddable grade badge.

Program staff, maintainers and vendors can check a feed on the public site or request a one-off score, track an agency through a submission form or a pull request, and gate a feed repository in CI with a marketplace action. Program rollups cover several agencies. The project sits between feed discovery sources and the agency's own publishing workflow. Its remediation workflow, which links an accepted fix to a recheck, is still being tested and is not yet a proven service.

Running it locally needs Python 3.12 or later, uv and Java 17 or later; the validator jar downloads on first run. A daily run writes the snapshot of configured feeds as JSON artifacts, and re-running the same day produces the same output. The web app reads those artifacts over HTTP and must be served from the repository root rather than opened as a file.

Limitations and requirements

Requires Python 3.12 or later, uv and Java 17 or later. The local web app must be served over HTTP; opening the page as a file leaves it stuck on loading. Realtime quality is scored only when a usable realtime feed is configured and measured; otherwise it is shown as not yet measured. Status is Beta, and the remediation workflow is still being tested. Matching agency_id to the five-digit NTD ID is optional.

Safety

Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.

  • Runs code or changes an assistant's behaviour

Sources

  • Official MCP Registry first seen 13 Nov 2026 · last seen 13 Nov 2026 · its page on the source
    GTFS Scorecard

    Read-only GTFS transit feed scorecards: grades, plain-language fixes, and history.

    v1.5.1
    As shown on registry.modelcontextprotocol.io when we last read it
MCP servers
hashicorp

Terraform MCP Server (HashiCorp)

HashiCorp's MCP server that gives an assistant current Terraform Registry information on providers, modules and policies, and can manage HCP Terraform workspaces.

1.6K GitHub starsCloud & DevOpsSoftware development
Updated 17 Nov 2026
MCP servers
neondatabase

Neon MCP Server (Postgres)

Neon's MCP server for managing Neon Postgres in plain language: create projects and branches, run queries and prepare schema migrations from your editor.

663 GitHub starsData & databasesSoftware development
Updated 17 Nov 2026
MCP servers
redis

Redis MCP Server

Redis's official MCP server that lets an AI assistant store, read and search data in a Redis database, including streams, JSON documents and vector indexes.

642 GitHub starsData & databasesSoftware development
Updated 17 Nov 2026
MCP servers
supabase-community

Supabase MCP Server

Supabase's MCP server that connects an AI assistant to your Supabase project to design tables, run queries, read configuration and look up documentation.

Data & databasesSoftware development
Updated 17 Nov 2026