# Court Listener [Health: Active]

**Category:** ⚖️ Legal  
**Repository:** https://github.com/pipeworx-io/mcp-court-listener  
**GitHub Stars:** 0  
**npm Downloads (last month):** 1034  
**Views:** 0  
**Installs:** 0  
**Upvotes:** 0  
**Directory Page:** https://allmcps.com/mcp/court-listener

## Description
CourtListener MCP — Free Law Project's CourtListener API (free, no auth required for basic access)

## Tools
Capabilities this server exposes over MCP:

- **find_case** — You know what the case is **called** — "Roe v. Wade", or just "Sullivan"
- **lookup_citation** — You have a reporter citation — "410 U.S. 113"
- **list_case_opinions** — You have a case and want its majority, concurrences and dissents
- **get_opinion** — You have an opinion id and want the **full text
- **search_opinions** — Case search by name, judge or category (mirror-first; a specific `court` code searches live)
- **search_dockets** — Docket-level search, upstream
- **list_docket_filings** — You have a `docket_id` and want the **docket sheet** — what was filed, when
- **get_docket_filing** — You have a `document_id` and want that one filing + its PDF
- **search_court_filings** — You want the **text of filings** — motions, briefs, orders — not opinions
- **find_case_patents** — Patent case → its asserted patent numbers (with USPTO metadata) → its defendants, in one call

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

```json
"mcpServers": {
  "court-listener": {
    "command": "npx",
    "args": ["-y","@pipeworx/mcp-court-listener"]
  }
}
```

## Documentation

## What Court Listener MCP server does

Court Listener MCP server exposes Free Law Project's CourtListener data through MCP tools for researching US case law and litigation records. The corpus contains approximately 8.3 million opinions from 3,361 courts, with coverage reaching back to 1761. State materials make up most of the collection, alongside federal, territorial, military, and tribal opinions.

The server separates judicial opinions from party filings. Opinion tools help identify what a court decided, while filing tools retrieve docket activity such as motions, briefs, orders, and other submitted documents. A patent-focused tool cross-references patent litigation with patent numbers and, when configured, USPTO metadata.

## How it works

For ordinary case research, use `find_case` when you know a case name, or `lookup_citation` when you have a reporter citation. Then pass the identified case to `list_case_opinions` to distinguish majority, concurring, and dissenting opinions, and use `get_opinion` for the complete text. Search results are ranked by citation count within CourtListener's corpus.

`search_opinions` supports searches by name, judge, category, or topic. It normally favors a local mirror, while a query with a specific court code searches upstream. Search results can include an excerpt from the most-cited matching case's lead opinion. Messy case names may receive a relaxed match after abbreviations, citation scaffolding, and corporate suffixes are removed; callers should verify the returned case name.

For litigation records, the intended sequence is `search_dockets`, `list_docket_filings`, and `get_docket_filing`. Docket tools use CourtListener `docket_id` values; a PACER case number does not resolve directly. Filing searches operate through CourtListener's upstream search path rather than the opinion mirror.

## Setup and configuration

Basic case lookup and opinion text work without an API key or signup. Topic searches and docket-related tools are subject to CourtListener throttling; a free Free Law Project token can lift that restriction.

`find_case_patents` can return asserted patent numbers without additional configuration. Setting `PLATFORM_USPTO_KEY` adds USPTO titles, statuses, grant dates, and first-inventor information to those numbers. The key is the same USPTO Open Data Portal credential used by the related patents pack.

## Tools and capabilities

- `find_case`: resolve a case by its name.
- `lookup_citation`: find a case from a reporter citation.
- `list_case_opinions`: enumerate majority, concurring, and dissenting opinions.
- `get_opinion`: retrieve the full text for an opinion ID.
- `search_opinions`: search opinions by topic, name, judge, category, or court.
- `search_dockets`: search docket-level records.
- `list_docket_filings`: list filings associated with a CourtListener docket ID.
- `get_docket_filing`: retrieve a filing and its PDF when one is available.
- `search_court_filings`: search filing text rather than opinion text.
- `find_case_patents`: identify patent numbers and defendants in a patent case, with optional USPTO metadata.

## Limitations and notes

Docket and topic searches are upstream and throttled. Without a token, filing tools have a budget of roughly 125 requests per day; opinion tools are unaffected. A docket entry may exist without a PDF because nobody has purchased that document through PACER. Patent extraction only finds patent references present in indexed docket text or available document text, so it is not a complete substitute for reviewing every complaint or filing.

Responses include a `snapshot_date`, and newer opinions may fall through to upstream search. About 14.2% of the opinion corpus is OCR-derived, and responses identify those records with `extracted_by_ocr`. `date_created` records when CourtListener received a record, not when the court filed or issued it; use `date_filed` for the ruling date. Citation counts measure references within CourtListener's corpus rather than universal legal importance.

_Full upstream README: https://allmcps.com/mcp/court-listener/readme_