The full upstream README, mirrored here for reference. Install config, tool schemas, adoption signals, and an original overview live on the Indiana BMV listing page.
Indiana DMV data: Bureau of Motor Vehicles (BMV) branches, self-service kiosks, BMV Connect locations, motorcycle rider-training (RSI) courses and skills-test sites. Keyless.
Part of Pipeworx — an MCP gateway connecting AI agents to 1476+ live data sources.
Indiana's agency is the Bureau of Motor Vehicles, universally the BMV. Hoosiers say "BMV branch" where other states say "DMV office", so the tool description names both.
| Tool | What it returns |
|---|---|
in_bmv_branches | Address, phone, hours, coordinates, kiosk flag and rider-training courses for all 160 published locations |
Filters: city, name, zip, location_type, kiosk_only, limit.
None. The source is a plain static JSON file on in.gov — no key, no query parameters, no
rate limit to negotiate. The whole file is fetched and filtered in code.
One file covers six categories, which is unusual — most states publish only their staffed offices. Live counts as of 2026-07-30:
typeLabel | Count |
|---|---|
| BMV Branch + Kiosk | 60 |
| BMV Branch | 56 |
| RSI Training Course & Skills Test | 22 |
| BMV Connect Location | 11 |
| RSI Training Course | 10 |
| Skills Test | 1 |
location_type accepts those exact labels and also plain words — "branch", "kiosk",
"connect", "motorcycle", "rider training", "skills test". kiosk_only: true is the
separate hasKiosk flag and keeps 72 of the 160 (the 60 "Branch + Kiosk" plus the
11 BMV Connect kiosks and one more).
These are live-verified behaviours, not guesses:
website is an empty string on 127 of 160 rows, not null. The tool normalises "" to
null so a caller can test for absence instead of comparing against the empty string.hours is null on 43 rows. RSI training courses and skills-test sites are run by partner
organisations (ABATE of Indiana, Harley dealers) that schedule by appointment rather than
posting counter hours; the tool leaves those null rather than inventing a schedule.url on an RSI row points at the partner, not at in.gov.county comes back null.46203-6063). The zip filter is a prefix match, so a
five-digit ZIP still matches."Indianapolis" returns 12 locations, and
several are motorcycle-training sites — use location_type="branch" when the caller wants a
place to renew a licence.bmv-branchmap-locations.jsonAdd to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):
tools/list at https://gateway.pipeworx.io/in-bmv/mcp returns the tools in the table
above plus the shared Pipeworx meta-tools — ask_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:
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.
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:
The gateway picks the right tool and fills the arguments automatically.
MIT