Fra Rail Safety MCP server

@pipeworx/fra-rail-safety

US railroad accidents, derailments and highway-rail grade crossing collisions reported to the Federal Railroad Administration, 1975 to the present: railroad, FRA cause code, location, casualties and damage per report, plus grouped counts.

Part of Pipeworx — an MCP gateway connecting AI agents to 1800+ live data sources. This is an independent, unofficial integration — not affiliated with, endorsed by, or published by the upstream provider.

Tools

— individual rail equipment accident reports (derailments, collisions, obstructions, fires), newest first, with the reporting railroad, accident type, FRA primary and contributing cause code and text, state/county, train speed, hazmat cars released, people evacuated, killed, injured, damage cost and a link to FRA's own report page.

• railaccidents(year?, state?, railroad?, causecode?, accidenttype?, mindamage_usd?, limit?)

— collisions between trains and road users at railroad crossings, newest first, with the USDOT crossing id, road name, road user type and action, vehicle and train speed, warning devices, weather, killed and injured.

• crossingincidents(state?, county?, city?, year?, railroad?, crossingid?, highwayuser?, fatalonly?, limit?)

— counts and casualty/damage totals grouped by railroad, cause, accident type, state, year or road user, for either dataset.

• railaccidentsummary(groupby, dataset?, year?, fromyear?, state?, railroad?, limit?)

Auth

Keyless.

Data sources

Equipment Accident/Incident Data (Form 54).

• Federal Railroad Administration, Office of Safety Analysis — Rail

Grade Crossing Incident Data (Form 57).

• Federal Railroad Administration, Office of Safety Analysis — Highway-Rail

Both are published by the US Department of Transportation and queried live on each call. US federal government work, public domain.

Things worth knowing:

railroads (joint operations, trackage rights) is filed once by each. FRA's unique-accident count keys on the incident key; railaccidentsummary reports both accidents (distinct) and railroad_reports.

• One row per railroad report, not per accident. An accident involving two

mark exactly (NS, UP, BNSF, CSX, ATK); longer input is a name substring (Norfolk Southern). A substring match on a reporting mark is wrong — NS occurs inside "CSX TRANSPORTATION".

• Railroad filter: 1-4 character input is matched against the reporting

code, crossings only the upper-case full name. The pack accepts either form and translates.

• State fields differ between the datasets: accidents carry a two-letter

current year is partial.

• Lag: railroads file monthly and FRA publishes a few months behind, so the

H human factors, E equipment, M miscellaneous); cause_code matches a prefix.

• Cause codes are FRA's: the first letter is the family (T track, S signal,

Quick Start

Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):

{
  "mcpServers": {
    "fra-rail-safety": {
      "url": "https://gateway.pipeworx.io/fra-rail-safety/mcp"
    }
  }
}

What this endpoint actually serves

tools/list at https://gateway.pipeworx.io/fra-rail-safety/mcp returns the tools in the table above plus the shared Pipeworx meta-tools — askpipeworx, discovertools, search_within, remember/recall and the rest of the gateway-wide set. So the tool count you see is larger than this table: a single-pack endpoint currently lists roughly 30 shared tools alongside the pack's own. The connection's initialize response states its exact scope, and is the authoritative answer for a given day.

Shortened. The full README is on GitHub.