Model Context Protocol (MCP) Documentation
Audioscrape provides a Model Context Protocol (MCP) server that allows AI assistants like Claude to directly access and search audio content. This enables AI models to provide contextual information from millions of hours of spoken content in real-time.
While we currently index over 1M hours of podcasts and conversations, we're expanding to include meetings, calls, interviews, live streams, and more audio sources.
Getting Started
The Audioscrape MCP server is available at mcp.audioscrape.com.
Our MCP implementation supports OAuth 2.0 authentication with dynamic client registration, following the MCP OAuth specification (6/18).
Available Tools
All tools have readOnlyHint: true - they only read data and never modify anything.
search_audio_content
Search across all indexed audio content including podcasts, interviews, and talks. Find discussions on any topic with speaker identification and timestamps.
Parameters
{
"query": {
"type": "string",
"description": "Search query text",
"required": true
},
"search_type": {
"type": "string",
"enum": ["text", "semantic"],
"default": "text",
"description": "Type of search: 'text' for keyword matching, 'semantic' for conceptual search"
},
"limit": {
"type": "integer",
"default": 50,
"minimum": 1,
"maximum": 200,
"description": "Maximum number of results"
},
"offset": {
"type": "integer",
"default": 0,
"description": "Offset for pagination"
},
"sort_by": {
"type": "string",
"enum": ["relevance", "date", "episode_title"],
"default": "relevance"
},
"sort_order": {
"type": "string",
"enum": ["asc", "desc"],
"default": "desc"
},
"filters": {
"type": "object",
"properties": {
"podcast_ids": {"type": "array", "items": {"type": "string"}},
"date_from": {"type": "string", "description": "YYYY-MM-DD"},
"date_to": {"type": "string", "description": "YYYY-MM-DD"},
"recency": {"type": "string", "enum": ["last_week", "last_month", "last_year"]}
}
},
"include_context": {
"type": "boolean",
"default": false,
"description": "Include surrounding segments for context"
}
}
Example Request
{
"query": "artificial intelligence ethics",
"search_type": "semantic",
"limit": 10,
"filters": {
"recency": "last_month"
}
}
Example Response
{
"results": [
{
"episode_id": "12345",
"episode_title": "The Future of AI Ethics",
"podcast_title": "Tech Talk Daily",
"segment_text": "The ethics of artificial intelligence is...",
"timestamp": "00:15:32",
"speaker": "Dr. Jane Smith",
"url": "https://www.audioscrape.com/episode/tech-talk/ai-ethics#t=932",
"relevance_score": 0.95
}
],
"total_results": 247,
"has_more": true
}
list_recent_episodes
List recent podcast episodes with optional filtering by podcast or time period.
Parameters
{
"limit": {
"type": "integer",
"default": 20,
"minimum": 1,
"maximum": 100,
"description": "Maximum number of episodes"
},
"podcast_ids": {
"type": "array",
"items": {"type": "string"},
"description": "Filter by specific podcast IDs"
},
"days_back": {
"type": "integer",
"default": 7,
"minimum": 1,
"maximum": 365,
"description": "Number of days to look back"
}
}
Example Request
{
"limit": 10,
"days_back": 3
}
Example Response
{
"episodes": [
{
"id": "12345",
"title": "Latest Tech News Roundup",
"podcast_title": "Tech Talk Daily",
"publish_date": "2024-12-15",
"duration_seconds": 3600,
"url": "https://www.audioscrape.com/episode/tech-talk/news-roundup"
}
],
"total": 10
}
get_episode_content
Get full content and metadata for a specific episode, including transcript and speaker information.
Parameters
{
"episode_id": {
"type": "string",
"required": true,
"description": "Episode ID to retrieve"
},
"include_segments": {
"type": "boolean",
"default": true,
"description": "Include full transcript segments"
},
"include_metadata": {
"type": "boolean",
"default": true,
"description": "Include metadata (speakers, entities)"
}
}
Example Request
{
"episode_id": "12345",
"include_segments": true,
"include_metadata": true
}
Example Response
{
"episode": {
"id": "12345",
"title": "The Future of AI Ethics",
"podcast_title": "Tech Talk Daily",
"publish_date": "2024-12-15",
"duration_seconds": 3600,
"description": "A deep dive into AI ethics..."
},
"segments": [
{
"start_time": "00:00:00",
"end_time": "00:02:30",
"text": "Welcome to Tech Talk Daily...",
"speaker": "Host"
},
{
"start_time": "00:02:30",
"end_time": "00:05:00",
"text": "Thank you for having me...",
"speaker": "Dr. Jane Smith"
}
],
"speakers": ["Host", "Dr. Jane Smith"],
"entities": [
{"name": "Artificial Intelligence", "type": "technology"},
{"name": "OpenAI", "type": "organization"}
]
}
browse_podcast
Browse episodes from a specific podcast series.
Parameters
{
"podcast_id": {
"type": "string",
"required": true,
"description": "Podcast ID to browse"
},
"limit": {
"type": "integer",
"default": 50,
"minimum": 1,
"maximum": 200
},
"offset": {
"type": "integer",
"default": 0
},
"sort_by": {
"type": "string",
"enum": ["date", "title"],
"default": "date"
}
}
Example Request
{
"podcast_id": "tech-talk-daily",
"limit": 20,
"sort_by": "date"
}
Example Response
{
"podcast": {
"id": "tech-talk-daily",
"title": "Tech Talk Daily",
"publisher": "Tech Media Inc",
"description": "Daily tech news and interviews"
},
"episodes": [
{
"id": "12345",
"title": "Latest Tech News",
"publish_date": "2024-12-15",
"duration_seconds": 3600
}
],
"total_episodes": 250,
"has_more": true
}
Authentication
The Audioscrape MCP server uses OAuth 2.0 with PKCE (Proof Key for Code Exchange) for secure authentication. The authentication flow is handled automatically by MCP-compatible clients like Claude Desktop.
OAuth Endpoints:
/oauth/register- Dynamic client registration/oauth/authorize- Authorization endpoint/oauth/token- Token exchange endpoint
Setting Up in MCP Clients
Claude Desktop Setup
For specific Claude Desktop instructions, see our Claude Desktop Setup Guide.
Claude Code Setup
For Claude Code CLI integration, see our Claude Code Setup Guide.
Other MCP Clients
Audioscrape works with any MCP-compatible client. Use the server URL:
https://mcp.audioscrape.com
The client will handle OAuth authentication automatically when you connect.
Rate Limits
To ensure fair usage and system stability, the following rate limits apply:
- • Search requests: 100 per minute
- • Episode/transcript requests: 200 per minute
- • List operations: 50 per minute
Example Prompts
Example queries you can ask Claude when connected:
- • "Find recent discussions about artificial intelligence ethics"
- • "Search for mentions of OpenAI in the last month"
- • "What are podcasters saying about the latest tech trends?"
- • "Get the full transcript of episode ID 12345"
- • "List the latest episodes from Lex Fridman Podcast"
Troubleshooting
Authentication Failed
Make sure you're logged into your Audioscrape account in your browser. The OAuth flow will open a browser window for authentication.
Connection Timeout
Check your internet connection and firewall settings. The MCP server runs on port 443 (HTTPS).
No Results Found
Try broader search terms or use semantic search for conceptual queries. Not all podcasts are indexed yet.
Support
For technical support or questions about the MCP integration, please contact us at [email protected].