MCP Radar
MCP Server

CoreWise

io.github.ryanportfolio/corewise
Knowledge & Documentation Media & Content Search & Research Public & reachable MCP 2026-07-28

What this MCP does

Extracts transcripts and structured summaries from videos, podcasts, articles, and PDFs, and searches a public library of prior extractions.

Capabilities

Tools

4 tools
extract_url
Start an AI extraction of a YouTube video, podcast, article, or PDF URL on CoreWise. Returns an extraction_id immediately after initialization. Initialization normally takes a few seconds but can take up to 2 minutes for videos without captions or for PDFs. The extraction itself then runs for 1-7 minutes: poll with get_extraction every 20-30 seconds until status is 'completed'. Results include a cross-validated synthesis plus per-model summaries. Requires an API key (create one at corewise.video, Profile page, 'API & MCP Keys'). Each call consumes one extraction from the key owner's monthly quota.
Input schema 
{'type': 'object', 'required': ['url'], 'properties': {'url': {'type': 'string', 'description': 'The video, podcast, article, or PDF URL to extract insights from.'}, 'models': {'type': 'array', 'items': {'enum': ['claude', 'openai', 'gemini', 'mercury', 'grok', 'mistral'], 'type': 'string'}, 'description': "Which AI models to run (1-6). Default: ['openai', 'gemini']. More models cost more time."}}}
get_extraction
Get the status and results of a CoreWise extraction by id. While status is 'processing', poll every 20-30 seconds. When status is 'completed' the response contains the structured synthesis (JSON object: summary, takeaways, highlights, notable quotes) and per-model markdown summaries. Works on your own extractions (API key required) and on public community extractions.
Input schema 
{'type': 'object', 'required': ['extraction_id'], 'properties': {'extraction_id': {'type': 'string', 'description': 'The extraction id returned by extract_url.'}}}
get_transcript
Get the raw source transcript (or article/PDF text) of a CoreWise extraction by id. Available as soon as the extraction has been initialized — no need to wait for 'completed'. Transcripts can be very long, so results are paged: pass 'offset' and 'max_chars' to fetch further chunks when 'truncated' is true. Works on your own extractions (API key required) and on public community extractions.
Input schema 
{'type': 'object', 'required': ['extraction_id'], 'properties': {'offset': {'type': 'number', 'description': 'Character offset to start from (default 0). Use with max_chars to page.'}, 'max_chars': {'type': 'number', 'description': 'Max characters to return (default 100000, max 200000).'}, 'extraction_id': {'type': 'string', 'description': 'The extraction id returned by extract_url or found via search.'}}}
search_public_extractions
Search CoreWise's public community library of extractions (videos, podcasts, articles, and PDFs already analyzed by other users). Returns titles, snippets, and share URLs. Useful to check whether a video has already been extracted before starting a new extraction. No API key required.
Input schema 
{'type': 'object', 'required': ['query'], 'properties': {'limit': {'type': 'number', 'description': 'Max results (default 10, max 25).'}, 'query': {'type': 'string', 'description': 'Search terms matched against titles and content.'}}}
History

Recent tool changes

Added
search_public_extractions
Sept. 17, 2026, 12:49 p.m.
Added
get_transcript
Sept. 17, 2026, 12:49 p.m.
Added
get_extraction
Sept. 17, 2026, 12:49 p.m.
Added
extract_url
Sept. 17, 2026, 12:49 p.m.
Discover

Similar MCP servers

NotebookLM

io.github.mcp-dir/notebooklm-mcp

Manages NotebookLM notebooks and sources, answers source-grounded questions with citations, and generates artifacts such as repor…

Archive

io.github.pipeworx-io/archive

Provides access to Internet Archive item metadata and downloadable files for researching and retrieving archived digital material…

Georgia Archives

io.github.pipeworx-io/georgia-archives

Searches and browses the National Archives of Georgia library, fonds, and film catalogues, and retrieves parsed archival library …

Bookbrainz

io.github.pipeworx-io/bookbrainz

Searches and retrieves structured BookBrainz metadata for books, authors, editions, publishers, series, and related entities.

Dpla

io.github.pipeworx-io/dpla

Searches and retrieves digitized photographs, documents, maps, books, and other cultural heritage records from the Digital Public…

Listen to Sadhu

app.listentosadhu/corpus

Provides semantic and lexical search across Vedic scriptures, commentaries, lectures, transcripts, and related audio and video co…

jakehandy.com

com.jakehandy/mcp

Searches, retrieves, cites, and supports reactions to Jake Handy’s articles, guides, profile, and other site pages.

Erik Bethke's Blog & Knowledge Graph

com.erikbethke/blog

Searches, retrieves, verifies, and traverses a long-running blog archive covering AI, energy, policy, games, and investing.