Ntsb Investigations MCP server

@pipeworx/ntsb-investigations

NTSB aviation accident/incident investigations, searchable by aircraft registration (tail number) or by make/model. Returns NTSB number, event date, location, injury level, phase/occurrence, probable cause, findings, and the NTSB docket link for each match.

Part of Pipeworx — an MCP gateway connecting AI agents to 1721+ live data sources. This is an independent, unofficial integration — not affiliated with, endorsed by, or published by the upstream provider.

Tools

— requires registration or make. model narrows within a make (matches "172", "172S", "172N", ... by prefix). year filters by event year, and is also how a registration match is narrowed when an N-number has been reassigned to a different aircraft over time (see below). Returns { found, dataasof, source, count, query, results[] }, or { found: false, dataasof, source, query } with no matches.

• ntsbsearchinvestigations({ registration?, make?, model?, year?, state?, limit? })

Auth

Keyless. No upstream account, no API key.

Data sources

database (avall.zip, a Microsoft Access .mdb bulk file, confirmed live 2026-10-07 at ~96 MB zipped / ~561 MB unzipped). This is the full, current dataset — the SAME data CAROL's aviation search queries, published as the bulk file NTSB itself ships for exactly this use.

• — the NTSB's own eADMS aviation accident

a given ntsb_number, where the final report and supporting documents are published. Confirmed live (HTTP 200) for a real case pulled from this same dataset.

• — the NTSB docket page for

Why not CAROL's own search, or the newer developer API

CAROL (data.ntsb.gov/carol-main-public), NTSB's modern search UI, was probed first. Its JSON endpoints (api/Query/Main, api/Query/FileExport) are undocumented, and every QueryGroups/QueryRules request shape reverse-engineered from a public third-party CAROL proxy and from NTSB's own CAROL-Guide.pdf returned HTTP 500 ("An unknown exception occured." / "An error has occurred.") — the frontend ships no devtools-free schema and the server gives no hint why the shape it wants differs from what a real browser session sends (likely a server-side session/anti-forgery requirement CAROL's own JS sets up before the first query).

NTSB also runs a newer REST API at developer.ntsb.gov (Aviation / Safety Recommendations / Data Dictionary APIs, via an Azure API Management gateway). That portal requires signing up for a developer account and a subscription key before any call succeeds — an authentication wall, which per this repo's standing rule is never a free pass to build around without a separate key decision, unlike the plain public bulk file this pack actually reads.

Refreshing the data

node mcps/ntsb-investigations/scripts/refresh.mjs [--local-mdb ] [--dry-run] [--r2-mode auto|api|wrangler] [--shard-max-bytes ]

Downloads avall.zip, unzips it, runs mdb-export (mdbtools — brew install mdbtools / apt install mdbtools) on five tables (aircraft, events, narratives, Findings, EventsSequence, eADMSPUBDataDictionary), joins them into one flat case-per-aircraft list, then shards it into the shared pipeworx-datasets R2 bucket (same bucket as mcps/indiana-code, mcps/illinois-code, mcps/crs-reports — see scripts/lib/statute-store.mjs) rather than writing one object:

Shortened. The full README is on GitHub.