Odel
Fmcsa

Fmcsa

@pipeworx-ioTypeScriptMITUpdated 1w ago

US motor-carrier registry: DOT/MC/name lookup, operating authority, safety — keyless

Server endpointStreamable HTTPNo authProbed

This is the third-party server itself — Odel doesn't run it. Hitting this URL directly talks straight to the upstream server with no auth or proxying. Connect through Odel to front it with managed auth.

FMCSA — US Motor Carrier Registry & Safety

Look up any US trucking or bus company by USDOT number, MC/docket number, or name, and pull its safety record: safety rating, out-of-service rates vs national averages, crash counts, and operating authority (including broker status).

Part of Pipeworx — an MCP gateway connecting AI agents to 1476+ live data sources.

Tools

ToolWhat it answers
fmcsa_carrier_lookupWho is this carrier? Legal/DBA name, address, status, fleet size, drivers, cargo types — by USDOT number, MC number, or name.
fmcsa_search_carriersFind carriers by name (partial match), ranked by fleet size, optional state filter.
fmcsa_operating_authorityIs this carrier authorized to operate or broker freight? MC docket + common/contract/broker authority status.
fmcsa_safety_snapshotHow safe is this carrier? Safety rating, driver/vehicle/hazmat out-of-service rates vs national averages, 24-month crash counts — plus SMS BASIC percentiles with a webKey.

Auth

Every tool works keyless. fmcsa_safety_snapshot uses the public SAFER Company Snapshot by default; pass a free FMCSA QCMobile webKey via _apiKey to add SMS BASIC category percentiles (Unsafe Driving, HOS Compliance, Vehicle Maintenance, ...). webKey signup (https://mobile.fmcsa.dot.gov/QCDevsite/docs/apiAccess) requires a login.gov account.

Note: a carrier whose biennial MCS-150 update lapsed shows as record_inactive — FMCSA publishes no safety snapshot for inactive USDOT numbers. That's an upstream data gap, not an outage; fmcsa_carrier_lookup still returns the last filed census record.

Data sources

Quick Start

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

{
  "mcpServers": {
    "fmcsa": {
      "url": "https://gateway.pipeworx.io/fmcsa/mcp"
    }
  }
}

What this endpoint actually serves

tools/list at https://gateway.pipeworx.io/fmcsa/mcp returns the tools in the table above plus the shared Pipeworx meta-toolsask_pipeworx, discover_tools, 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.

This is deliberate, not multiplexing by accident. The meta-tools are what let a scoped connection answer a question this pack does not cover — via ask_pipeworx, which routes across the whole catalog — without you adding a second MCP server. There is currently no way to mount a pack endpoint without them; if the extra schemas cost you more context than the routing is worth, connect to the full gateway once rather than to several pack endpoints.

Or connect to the full Pipeworx gateway to get every pack's tools listed directly, instead of just this one's:

{
  "mcpServers": {
    "pipeworx": {
      "url": "https://gateway.pipeworx.io/mcp"
    }
  }
}

Both URLs reach the same gateway and the same 1476+ data sources. The only difference is which pack's tools are listed directly; ask_pipeworx reaches all of them from either one.

Using with ask_pipeworx

Instead of calling tools directly, you can ask questions in plain English — this works on the pack endpoint above as well as on the full gateway:

ask_pipeworx({ question: "your question about Fmcsa data" })

The gateway picks the right tool and fills the arguments automatically.

More

License

MIT