CoreWise

Official3 tools

by ryanportfolio

Extract structured insights from videos, podcasts, articles, and PDFs with multi-model AI

io.github.ryanportfolio/corewise — MCP Server

This MCP server, io.github.ryanportfolio/corewise, provides tooling to extract structured insights from videos, podcasts, articles, and PDFs using multi-model AI. It is identified by slug io-github-ryanportfolio-corewise and exposes 3 tools (toolCount: 3).

🛠️ Key Features

Extract structured insights from videos
Extract structured insights from podcasts
Extract structured insights from articles
Extract structured insights from PDFs
Uses multi-model AI

🚀 Use Cases

Turn video content into structured insights
Turn podcast content into structured insights
Analyze articles to produce structured insights
Parse PDF documents to extract structured insights

⚡ Developer Benefits

Consistent workflow across multiple content types
Multi-model AI approach for insight extraction
3 available tools for server integration

Captured live from the server via tools/list.

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.

Parameters2

url	string	required	The video, podcast, article, or PDF URL to extract insights from.
models	array	optional	Which AI models to run (1-6). Default: ['claude', 'gemini']. More models cost more time.

Raw schema

{
  "type": "object",
  "properties": {
    "url": {
      "type": "string",
      "description": "The video, podcast, article, or PDF URL to extract insights from."
    },
    "models": {
      "type": "array",
      "items": {
        "type": "string",
        "enum": [
          "claude",
          "openai",
          "gemini",
          "mercury",
          "grok",
          "mistral"
        ]
      },
      "description": "Which AI models to run (1-6). Default: ['claude', 'gemini']. More models cost more time."
    }
  },
  "required": [
    "url"
  ]
}

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.

Parameters1

extraction_id

string

required

The extraction id returned by extract_url.

Raw schema

{
  "type": "object",
  "properties": {
    "extraction_id": {
      "type": "string",
      "description": "The extraction id returned by extract_url."
    }
  },
  "required": [
    "extraction_id"
  ]
}

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.

Parameters2

query	string	required	Search terms matched against titles and content.
limit	number	optional	Max results (default 10, max 25).

Raw schema

{
  "type": "object",
  "properties": {
    "query": {
      "type": "string",
      "description": "Search terms matched against titles and content."
    },
    "limit": {
      "type": "number",
      "description": "Max results (default 10, max 25)."
    }
  },
  "required": [
    "query"
  ]
}

Install

Tools (3)

extract_urlget_extractionsearch_public_extractions

Remote endpoint

Streamable HTTP

Hosted server - connect over the network, no local install.

url

https://corewise.video/mcp

Add to VS Code Add to Cursor

claude_desktop_config.json

json

{
  "mcpServers": {
    "corewise": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://corewise.video/mcp"
      ]
    }
  }
}

Desktop config is stdio-only; this bridges via mcp-remote. Native remote: Settings > Connectors.

io.github.ryanportfolio/corewise — MCP Server

🛠️ Key Features

🚀 Use Cases

⚡ Developer Benefits

extract_url

get_extraction

search_public_extractions

Install

Remote endpoint

Related servers