
Connects to the FBI's National Stolen Art File, a public database of stolen artworks and cultural property. The source doesn't detail specific tools, but you'd use this when building applications that need to cross-reference art provenance, verify artwork legitimacy, or flag potentially stolen pieces in gallery or auction systems. Runs through Pipeworx's gateway with no authentication required, and you can query it either by calling tools directly or using their ask_pipeworx interface that interprets natural language questions. Part of a larger gateway offering 764+ data sources if you need to combine art crime data with other investigative or cultural heritage APIs.
FBI Art Crimes MCP — FBI National Stolen Art File (free, no auth).
Part of Pipeworx — an MCP gateway connecting AI agents to 1481+ live data sources.
| Tool | Description |
|---|---|
list_art_crimes | Browse or search the FBI National Stolen Art File — stolen and missing artworks under active FBI art theft investigations. Returns artwork UIDs, titles, descriptions, maker/artist, materials, measurements, period, and a thumbnail image URL. Filter by title or maker substring. Use page to paginate. Pass a UID into get_art_crime for the full record. |
get_art_crime | Get the full record for a single stolen or missing artwork from the FBI National Stolen Art File by UID. Returns title, full description, crime category, maker/artist, materials, measurements, period, additional data, all images, and the FBI case URL. Use a UID returned by list_art_crimes. |
Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):
{
"mcpServers": {
"fbi_artcrimes": {
"url": "https://gateway.pipeworx.io/fbi_artcrimes/mcp"
}
}
}
tools/list at https://gateway.pipeworx.io/fbi_artcrimes/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:
{
"mcpServers": {
"pipeworx": {
"url": "https://gateway.pipeworx.io/mcp"
}
}
}
Both URLs reach the same gateway and the same 1481+ 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:
ask_pipeworx({ question: "your question about Fbi Artcrimes data" })
The gateway picks the right tool and fills the arguments automatically.
MIT
curl -X POST https://gateway.pipeworx.io/v1/tools/list_art_crimes \
-H 'Content-Type: application/json' \
-d '{"title":"painting","maker":"Picasso"}'
No account needed for the first calls. Inspect any tool: GET https://gateway.pipeworx.io/v1/tools/list_art_crimes. Find one: POST https://gateway.pipeworx.io/v1/tools/search_packs with {"query":"..."}.