Server data from the Official MCP Registry
US business bankruptcy data via MCP: search by name, EIN. Lookup docket items.
US business bankruptcy data via MCP: search by name, EIN. Lookup docket items.
Remote endpoints: streamable-http: https://mcp.bankruptcyobserver.com/mcp
Valid MCP server (1 strong, 1 medium validity signals). No known CVEs in dependencies. Imported from the Official MCP Registry.
Endpoint verified · Requires authentication · 1 issue found
Security scores are indicators to help you make informed decisions, not guarantees. Always review permissions before connecting any MCP server.
This plugin requests these system permissions. Most are normal for its category.
Remote Plugin
No local installation needed. Your AI client connects to the remote endpoint directly.
Add this to your MCP configuration to connect:
{
"mcpServers": {
"com-bankruptcyobserver-mcp": {
"url": "https://mcp.bankruptcyobserver.com/mcp"
}
}
}From the project's GitHub README.
Public documentation and registry metadata for the Bankruptcy Observer API and MCP server. This repository contains no application source code.
Data covers US business bankruptcies (federal courts) only. Consumer-only filings and non-US jurisdictions are not included.
AI assistants and users can look up bankruptcy cases with no account, no API key, and no API token:
| Free query | MCP tool | Example |
|---|---|---|
| Debtor name | search_bankruptcy_cases_tool | search_term: "JOY-CPW, INC." — no court required |
| Case number | get_case_by_case_number_tool | short_case_number: "26-10543" — no court required |
Docs: https://mcp.bankruptcyobserver.com/docs or https://api.bankruptcyobserver.com/docs (GET, no auth). The MCP root GET https://mcp.bankruptcyobserver.com/ also returns a free_lookups hint.
You can sign up for a subscription through the MCP server: use list_plans_tool to see plans, then purchase_plan_tool with plan_id (e.g. professional, business, enterprise) to get a Stripe Checkout link. After payment you receive an API token; restricted queries can be authenticated with that token or with OAuth Bearer access tokens from the MCP OAuth flow. No need to go to the website to subscribe.
For questions about access, billing, or data coverage, use only the contact form at https://www.bankruptcyobserver.com/contact. Do not publish or use direct email addresses for contact.
Paid plans (Stripe via MCP tools)
Billable tool calls correspond to data tools invoked via MCP (for example, search, case by EIN, docket items, NAICS/state filters) or their REST API equivalents.
Authenticate using either an API token or an OAuth access token, sent in one of these ways:
Authorization: Bearer <your-token>X-API-Key: <your-token>Api-Key: <your-token>Use OpenAI's Responses API to call this MCP server directly.
Free tier (no token):
from openai import OpenAI
client = OpenAI()
response = client.responses.create(
model="gpt-4.1",
tools=[{
"type": "mcp",
"server_label": "bankruptcy_observer",
"server_url": "https://mcp.bankruptcyobserver.com/mcp",
"require_approval": "never",
}],
input="Search for bankruptcy cases for Acme Corp",
)
print(response.output_text)
Paid tier (with token):
response = client.responses.create(
model="gpt-4.1",
tools=[{
"type": "mcp",
"server_label": "bankruptcy_observer",
"server_url": "https://mcp.bankruptcyobserver.com/mcp",
"headers": {"Authorization": "Bearer YOUR_TOKEN"},
"require_approval": "never",
}],
input="Get docket entries for case 24-10543",
)
Note: Do not set
Content-TypeorAcceptheaders manually — the OpenAI client sets these correctly for the MCP protocol. Overriding them will cause the server to return an HTML error page instead of a JSON response.
OAuth option: Connectors such as ChatGPT can also authenticate with MCP OAuth and send Bearer access tokens automatically after login. API token headers are still supported.
To connect this MCP server in ChatGPT with OAuth, create a new app/connector and enter the OAuth endpoints below exactly.
If the Registration URL is omitted, Dynamic Client Registration will fail and ChatGPT will connect without usable tool authorization.
OAuth endpoints
https://mcp.bankruptcyobserver.com/authorizehttps://mcp.bankruptcyobserver.com/tokenhttps://mcp.bankruptcyobserver.com/registerhttps://mcp.bankruptcyobserver.com/https://mcp.bankruptcyobserver.com/mcpAfter connecting, ChatGPT should complete OAuth in-browser and then call tools using OAuth Bearer tokens. Legacy API-token headers remain supported for clients that use header auth.
| Service | Endpoint | Auth |
|---|---|---|
| REST API | https://api.bankruptcyobserver.com/api/v1/... | Free lookups: no auth. Restricted queries: API token or OAuth Bearer token |
| MCP | https://mcp.bankruptcyobserver.com/mcp | Free lookups: no auth. Restricted queries: API token or OAuth Bearer token |
| Docs | https://api.bankruptcyobserver.com/docs or https://mcp.bankruptcyobserver.com/docs | None |
The /mcp path is the MCP protocol endpoint (POST only). For human-readable documentation, use the Docs URLs above (GET, no auth).
The same queries are available on both the REST API and the MCP server. Each query returns JSON; case-level responses include the standard fields below unless noted.
| # | Query | Inputs | What you get | Notes |
|---|---|---|---|---|
| 1 | Search | search_term, limit, skip, optional court_id or court_state | List of cases with standard fields | FREE (no key): exact name returns limited info; full details are available with a paid plan. Otherwise: prefix (starts-with) on name; use *term for contains. For case number use Case by case number. |
| 2 | Case by EIN | ein | One case (or none) + einInDatabase: "Yes" or "No" | Single match; flag says whether we have this EIN. (Restricted: API token or OAuth Bearer token.) |
| 3 | Docket items | shortCaseNumber, optional court_id or court_state, limit | Case identifier, dateDocketUpdated, list of entries (itemNumber, itemText, itemDate, …) | Case resolved by short case number + optional court. (Restricted: API token or OAuth Bearer token.) |
| 4 | Case by case number | shortCaseNumber; optional court_state or court_id for paid disambiguation | List (free) or one case (paid) | FREE (no key): case number only, no court required; returns all matching cases. For paid requests, you may provide court_state/court_id to select a specific case when multiple courts match. |
| 5 | Cases by NAICS | naics (2–4 digits), limit, optional start_date, end_date | List of cases with standard fields | NAICS must be 2–4 digits; more than 4 is rejected. |
| 6 | Cases by state | state (2-letter), limit, optional start_date, end_date | List of cases with standard fields | Optional date range on dateFiled. |
| 7 | Case status / dates | — | Returned as part of case data | dateFiled, dateClosed, dateDismissed; isOpen / isClosed / isDismissed. |
Pagination: List responses support limit and skip where applicable; responses include total or similar where useful.
Date range: For NAICS and state queries, optional start_date and end_date filter on dateFiled. Search does not support date filters.
Returned for any query that returns case rows:
| Field | Description |
|---|---|
| name | Debtor/case name |
| court | Court name |
| shortCaseNumber | Short case number (e.g. 22-12345) |
| dateDocketUpdated | When docket/case data was last updated in our system |
| dateFiled | Filing date |
Optional (included when relevant): courtState, chapter, NAICS, industry, dateClosed, dateDismissed, isOpen / isClosed / isDismissed, assetAmount, liabAmount.
einInDatabaseFor Case by EIN the response always includes:
einInDatabase — "Yes" if we have at least one case with this EIN (and the case payload); "No" if we have no case with this EIN (case payload null or omitted).For Docket items you get:
itemNumber, itemText, itemDate (and optionally pageCount, pacerDocId).| Query | REST API (POST) | MCP tool |
|---|---|---|
| Search | /api/v1/search | search_bankruptcy_cases_tool |
| Case by EIN | /api/v1/case/ein | get_case_by_ein_tool |
| Docket items | /api/v1/docket | get_docket_entries_tool |
| Case by case number | /api/v1/case/by-number | get_case_by_case_number_tool |
| Cases by NAICS | /api/v1/cases/by-naics | get_cases_by_naics_tool |
| Cases by state | /api/v1/cases/by-state | get_cases_by_state_tool |
Same backend for both; response shape is identical.
The full spec (same content as above, plus any updates) is also served with no auth at:
Both URLs return the same Markdown. Use them for the latest version or for AI/bot discovery.
This repo includes a server.json for the Official MCP Registry. It describes the remote MCP server and how to connect (URL + API token header). Use it when publishing to the registry via the Registry CLI; the registry points to this GitHub repo for metadata only.
Documentation and metadata in this repository are provided for discovery and integration. The Bankruptcy Observer product, API, and MCP service are offered under separate terms; see the product website.
Be the first to review this server!
by Modelcontextprotocol · Developer Tools
Read, search, and manipulate Git repositories programmatically
by Toleno · Developer Tools
Toleno Network MCP Server — Manage your Toleno mining account with Claude AI using natural language.
by mcp-marketplace · Developer Tools
Create, build, and publish Python MCP servers to PyPI — conversationally.
by Microsoft · Content & Media
Convert files (PDF, Word, Excel, images, audio) to Markdown for LLM consumption
by mcp-marketplace · Developer Tools
Scaffold, build, and publish TypeScript MCP servers to npm — conversationally
by mcp-marketplace · Finance
Free stock data and market news for any MCP-compatible AI assistant.