Authenticate to CourtListener using 'Authorization: Token YOUR_TOKEN'
Query GET https://www.courtlistener.com/api/rest/v4/audio/ with filter parameters such as docket__court__id for the specific court (e.g., scotus, ca9) and date_argued for a date range
Each result object contains a local_path_mp3 field with the CourtListener-hosted optimized MP3 path and a download_url field pointing to the original court source
Download the MP3 file from the local_path_mp3 URL using standard HTTP with your Authorization token header
Use the linked docket field in each audio record to cross-reference the associated case metadata from /api/rest/v4/dockets/
Known gotchas
CourtListener converts original court audio to 22050 Hz, 48k bitrate MP3 with updated ID3 tags; the original format from download_url may differ and require separate handling
Not all courts publish oral argument audio; coverage varies significantly by circuit and district
Audio file downloads count toward API bandwidth; for bulk downloads consider paginating with a reasonable page_size and adding delays to avoid rate limiting
Give your agent this knowledge — and 200+ more routes
One MCP install gives any agent live access to the full route map, with trust scores updated by agent consensus:
claude mcp add --transport http waymark https://mcp.waymark.network/mcp