Bankruptcy — US business bankruptcy filings

Business bankruptcy filings from US federal bankruptcy courts: 1.55 million filings, searchable by company name, court and date. No API key.

Part of Pipeworx — an MCP gateway connecting AI agents to 1863+ live data sources. This is an independent, unofficial integration — not affiliated with, endorsed by, or published by the upstream provider.

Auth

None.

Related MCP server: SEC EDGAR MCP

What this is, and what it is not

This is docket metadata: that a case exists, who filed, in which court, when it was filed, when it terminated, and which judge was assigned. It contains no filings — no petitions, schedules, motions or orders. Those live in RECAP, a separate corpus that is not keyless.

An agent that has this data knows a company filed. It does not know what the company said.

Consumer bankruptcy is deliberately excluded

Of CourtListener's 71,677,647 dockets, 35,312,051 are individual bankruptcy filings — half the corpus. They carry no business signal and are PII-adjacent, so they are excluded.

The docket export has no chapter column, so business and consumer are separated by a legal-entity-suffix test on the debtor name (Inc, LLC, Corp, Holdings, Construction, and so on), applied only inside bankruptcy courts. Two consequences worth knowing before relying on a negative result:

• A sole proprietorship filing under a personal name will not appear here.

• "No filings found" means "no business filing matched", never "this entity has never filed".

Tools

Court ids follow CourtListener's convention: nysb (S.D.N.Y. Bankruptcy), deb (Delaware), txsb (S.D. Tex.), cacb (C.D. Cal.), ilnb (N.D. Ill.).

Caveats

• Quarterly snapshot. Every response carries snapshot_date. Anything filed after it is not here.

• date_terminated is 78.3% filled, so a missing termination date means not recorded, never still open. Responses say this on every row.

• nature_of_suit is sparse (14.8% corpus-wide) and cannot be relied on to filter by case type.

• Case names are as the court recorded them, including abbreviations and inconsistent entity suffixes. Search matches substrings for that reason.

Attribution

Data is CourtListener / Free Law Project, published under the Public Domain Mark. Free Law Project funds and maintains the corpus. If this pack is useful to you, https://free.law/donate/ is where that goes.

Quick Start

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

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

What this endpoint actually serves

tools/list at https://gateway.pipeworx.io/bankruptcy/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 1863+ data sources. The only difference is which pack's tools are listed directly; ask_pipeworx reaches all of them from either one.

No MCP client? Call it over HTTP

curl -X POST https://gateway.pipeworx.io/v1/tools/bankruptcy_search \
  -H 'Content-Type: application/json' \
  -d '{"company":"Kmart","limit":5}'

No account needed for the first calls. Inspect any tool: GET https://gateway.pipeworx.io/v1/tools/bankruptcy_search. Find one: POST https://gateway.pipeworx.io/v1/tools/search_packs with {"query":"..."}.

Run it from npm

@pipeworx/mcp-bankruptcy is a local stdio bridge to the Pipeworx gateway: your MCP client starts it with npx, and it forwards every call to the same https://gateway.pipeworx.io/bankruptcy/mcp endpoint shown above. It needs network access; there is no offline mode.

{
  "mcpServers": {
    "bankruptcy": {
      "command": "npx",
      "args": ["-y", "@pipeworx/mcp-bankruptcy"]
    }
  }
}

Without a key it calls anonymously, capped at 50 calls a day. A free account raises that to 200 a day: get a key at https://pipeworx.io/signup and add "env": { "PIPEWORX_API_KEY": "<your key>" } to the server entry. The key is sent as a Bearer token, the same way a hosted connection sends it, so calls are metered and billed exactly as they are there.

It lists only this pack's tools by default. Set PIPEWORX_META_TOOLS=1 to also list ask_pipeworx and the other gateway-wide tools.

Behind an HTTPS proxy: Node's built-in fetch does not read HTTPS_PROXY by default. Newer Node releases honour it when NODE_USE_ENV_PROXY=1 is set; check your Node version's documentation.

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 Bankruptcy data" })

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

More

• Docs and guides

• pipeworx.io

License

MIT