# CourtAPI — Federal Court Data [Health: Active]

**Category:** ⚖️ Legal  
**Repository:** https://github.com/courtio/courtapi-mcp  
**GitHub Stars:** 0  
**npm Downloads (last month):** 162  
**Views:** 3  
**Installs:** 0  
**Upvotes:** 0  
**Directory Page:** https://allmcps.com/mcp/courtapi-federal-court-data

## Description
Search and retrieve US federal court cases, dockets, claims, and documents via PACER

## Tools
Capabilities this server exposes over MCP:

- **find_cases** — Discover federal court cases you don't have the court+number for yet. Pass a party/company name, a (partial) case number, or free-text keywords. Returns court_code + case_number needed by all other tools. No PACER cost. Note: keyword search (search-filings) charges 1 CourtAPI API call per 25 results returned. Examples: query='Sbarro', query='1:14-bk', query='retail chapter 11 2026'.
- **get_case** — Get all metadata for a known case: title, chapter, judge, key dates (filed/closed/discharged), assets, liabilities, and links to sub-resources (dockets, claims, parties, etc.) with their last-modified timestamps. Always call this first after finding a case. The response includes a 'menu' object where each entry has a 'modified' timestamp (null = never purchased) showing what sub-resources are available. Free unless include_live_pacer=true.
- **get_dockets** — Get the docket sheet for a case — all filings in chronological order with dates, descriptions, and attached document info (is_cached, download_cost). The header includes judge, attorneys, trustees, and 341 meeting date. Supports keyword search and date/number range filtering. Free unless include_live_pacer=true.
- **get_document** — Get a PDF attached to a docket entry. Always checks the cache first. If cached (is_cached=true), returns download_url + preview_url + ocr_link at no cost. If not cached and purchase=true, buys from PACER and returns download_url + receipt. If not cached and purchase=false (default), returns cost info so you can decide. docket_seq comes from docket entries (e.g. '42.00000'). part defaults to 1 (main doc).
- **get_claims** — Get the bankruptcy claims register — all proofs of claim filed by creditors, with amounts (filed/allowed/paid), claim type (secured/unsecured), creditor names, and filing dates. Essential for Chapter 11 analysis and creditor research. Supports keyword search and date/number range filtering.
- **get_parties** — Get all parties in a case (debtors, creditors, plaintiffs, defendants, trustees) and optionally their attorneys with firm name, contact info, and bar number. Useful for conflicts checks, service lists, and identifying who is involved.
- **get_creditors** — Get the creditor list for a bankruptcy case — all creditors scheduled in Schedules D/E/F, whether or not they filed a proof of claim. Different from get_claims (which shows filed proofs of claim).
- **ncl_search** — Search PACER's National Case Locator across all federal courts at once. More comprehensive than find_cases for party name searches — queries PACER directly. Costs PACER credits. Returns up to ~50 cases per page; pass search_id + page to paginate. Use for: finding a person's cases across all courts, SSN lookups, cross-court party searches.
- **list_courts** — List all PACER courts with their court codes. Call this when you need a court_code and don't know it. Returns ~200 courts; use type to filter. Common codes: nysbke, debke, ilnbke, cacdbe, txnbke.
- **get_pacer_credentials** — Check or update PACER credentials stored in CourtAPI. PACER credentials are required before any include_live_pacer=true call. action='check'    → show stored username (password not returned). action='set'      → store pacer_user + pacer_pass. action='validate' → test credentials without storing. action='delete'   → remove stored credentials.

## Claude Desktop Quick Installation
Install path detected from listing signals. Uses `npx` (confidence: high):

```json
"mcpServers": {
  "courtapi-federal-court-data": {
    "command": "npx",
    "args": ["-y","@courtio/courtapi-mcp"],
    "env": {
      "COURTAPI_APP_ID": "",
      "COURTAPI_APP_KEY": "",
      "COURTAPI_BASE_URL": ""
    }
  }
}
```

**Requires environment variables:** `COURTAPI_APP_ID`, `COURTAPI_APP_KEY`, `COURTAPI_BASE_URL` — the values above are empty placeholders; fill in real credentials before running (see the repository for what each one is for).

## Documentation

## What CourtAPI — Federal Court Data does

CourtAPI — Federal Court Data MCP server exposes CourtAPI’s federal court data through MCP tools. It covers bankruptcy, district, and appellate courts in the United States, including case metadata, docket activity, bankruptcy claims, scheduled creditors, parties, attorneys, and documents attached to filings. State courts are outside its stated coverage.

Case discovery can use party or company names, partial case numbers, or filing keywords. The result supplies the court code and full case number needed by the other case-level tools. A separate National Case Locator search queries PACER across courts and supports filters such as chapter, court, case number, date range, and certain name or SSN/TIN searches.

## How it works

The server uses stdio by default and can also run with Streamable HTTP. An MCP host sends tool calls to the local process, which uses CourtAPI credentials to access the API. Live PACER operations require PACER credentials stored through the credential-management tool.

A typical workflow starts with case discovery, followed by a case metadata lookup. The metadata includes a menu showing available sub-resources and their modification status. Docket results include filing details and document metadata, including whether a PDF is cached and its potential download cost. Docket entries can also include extracted dates and time zones for deadlines or hearings.

Document retrieval checks the CourtAPI cache first. Cached files can return download, preview, and OCR links without a new purchase. For an uncached document, the tool can report the cost before purchase; setting the purchase option buys the PDF from PACER and caches it for later requests.

## Setup and configuration

Create a CourtAPI account and obtain an application ID and application key from the developer portal. Configure them as `COURTAPI_APP_ID` and `COURTAPI_APP_KEY`. The API base URL can optionally be changed with `COURTAPI_BASE_URL`; otherwise, the default CourtAPI endpoint is used.

For Claude Desktop, configure the server with `npx -y @courtio/courtapi-mcp` and the two required credentials, then restart the client. Other MCP hosts can use the same stdio command and environment pattern. HTTP mode can be started with the `--http` flag and a `PORT` value.

Live PACER access also requires a PACER account. PACER fees are passed through for applicable live requests and document purchases. CourtAPI provides a free 30-day sandbox with stated request limits.

## Tools and capabilities

- `find_cases` selects an appropriate party, case-number, or filing-keyword search.
- `get_case` returns title, chapter, judge, dates, financial fields, and resource status.
- `get_dockets` retrieves filings with keyword and date or number filters.
- `get_document` previews cost status or purchases and returns a PDF link.
- `get_claims` filters bankruptcy proofs of claim by type and sorting fields.
- `get_parties` returns case participants and optionally attorney details.
- `get_creditors` reads scheduled creditors separately from filed claims.
- `ncl_search` performs cross-court PACER National Case Locator searches.
- `list_courts` returns court names and codes by court type.
- `get_pacer_credentials` checks, stores, validates, or deletes PACER credentials.

## Limitations and notes

The API requires long-form PACER case numbers for case-specific requests. Live docket refreshes should include a starting filing date to avoid buying the entire docket history. PACER charges can apply to live docket, claims, creditor, or case refreshes, National Case Locator searches, and uncached document purchases. CourtAPI API usage has separate plan-based limits and charges, including keyword-search usage by result volume.

_Full upstream README: https://allmcps.com/mcp/courtapi-federal-court-data/readme_