Ireader

Provides tools to read and extract content from webpages, transcripts, tweets, PDFs, and public Google Docs via MCP

typescript

0

GitHub Stars

typescript

Language

6 months ago

First Indexed

3 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "zlatanpham-ireader-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@x-mcp/ireader@latest"
      ]
    }
  }
}

iReader MCP is a server that helps you read and extract content from the internet by exposing a set of tools through the MCP protocol. It enables you to fetch webpage content, YouTube transcripts, tweet threads, PDFs, and public Google Docs in a standardized way for your applications and clients.

How to use

You connect your MCP client to the iReader MCP server to access its content extraction tools. Use the client to request data from supported sources such as webpages, videos, tweets, PDFs, and public Google Docs. You can orchestrate multiple tool calls in a single session to surface the exact text you need for downstream processing, summaries, or analysis.

How to install

Prerequisites: ensure you have Node.js and a suitable package manager installed on your system.

# Clone the repository
git clone https://github.com/zlatanpham/ireader-mcp.git
cd ireader-mcp

# Install dependencies
pnpm install

# Start the development server for testing the MCP tools
pnpm dev

Additional notes and examples

If you want to run iReader MCP through a local runtime or via a client like Claude Desktop, you can configure an MCP server entry to run the package with the runtime command shown in the examples.

{
  "mcpServers": {
    "ireader": {
      "command": "npx",
      "args": ["-y", "@x-mcp/ireader@latest"]
    }
  }
}

Another local runtime option

If you prefer to run the server directly from a local project path, use the runtime command shown here.

{
  "mcpServers": {
    "ireader": {
      "command": "npx",
      "args": ["tsx", "/PATH/TO/YOUR_PROJECT/src/index.ts"]
    }
  }
}

Available tools

get_webpage_markdown

Fetches the content of a webpage using Jina reader.

get_youtube_transcript

Fetches the transcript of a YouTube video.

get_tweet_thread

Fetches the thread of a tweet.

get_pdf

Extracts text content from a PDF file.

get_public_google_doc_markdown

Fetches the markdown content of a public Google Doc by URL.