Skip to main content
Glama

MCP NPX Fetch

npm version License: MIT TypeScript Model Context Protocol

A powerful MCP server for fetching and transforming web content into various formats (HTML, JSON, Markdown, Plain Text) with ease.

Installation • Features • Usage • Documentation • Contributing


🚀 Features

  • 🌐 Universal Content Fetching: Supports HTML, JSON, plain text, and Markdown formats

  • 🔒 Custom Headers Support: Add authentication and custom headers to your requests

  • 🛠 Built-in Transformations: Automatic conversion between formats

  • ⚡ High Performance: Built with modern JavaScript features and optimized for speed

  • 🔌 MCP Compatible: Seamlessly integrates with Claude Desktop and other MCP clients

  • 🎯 Type-Safe: Written in TypeScript with full type definitions

Related MCP server: webfetch-camouflage

📦 Installation

NPM Global Installation

npm install -g @tokenizin/mcp-npx-fetch

Direct Usage with NPX

npx @tokenizin/mcp-npx-fetch

📚 Documentation

Available Tools

fetch_html

Fetches and returns raw HTML content from any URL.

{
  url: string;     // Required: Target URL
  headers?: {      // Optional: Custom request headers
    [key: string]: string;
  };
}

fetch_json

Fetches and parses JSON data from any URL.

{
  url: string;     // Required: Target URL
  headers?: {      // Optional: Custom request headers
    [key: string]: string;
  };
}

fetch_txt

Fetches and returns clean plain text content, removing HTML tags and scripts.

{
  url: string;     // Required: Target URL
  headers?: {      // Optional: Custom request headers
    [key: string]: string;
  };
}

fetch_markdown

Fetches content and converts it to well-formatted Markdown.

{
  url: string;     // Required: Target URL
  headers?: {      // Optional: Custom request headers
    [key: string]: string;
  };
}

🔧 Usage

CLI Usage

Start the MCP server directly:

mcp-npx-fetch

Or via npx:

npx @tokenizin/mcp-npx-fetch

Claude Desktop Integration

  1. Locate your Claude Desktop configuration file:

    • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json

    • Windows: %APPDATA%/Claude/claude_desktop_config.json

    • Linux: ~/.config/Claude/claude_desktop_config.json

  2. Add the following configuration to your mcpServers object:

{
  "mcpServers": {
    "fetch": {
      "command": "npx",
      "args": ["-y", "@tokenizin/mcp-npx-fetch"],
      "env": {}
    }
  }
}

💻 Local Development

  1. Clone the repository:

git clone https://github.com/tokenizin-agency/mcp-npx-fetch.git
cd mcp-npx-fetch
  1. Install dependencies:

npm install
  1. Start development mode:

npm run dev
  1. Run tests:

npm test

🛠 Technical Stack

🤝 Contributing

Contributions are welcome! Please feel free to submit a Pull Request. For major changes, please open an issue first to discuss what you would like to change.

  1. Fork the repository

  2. Create your feature branch (git checkout -b feature/AmazingFeature)

  3. Commit your changes (git commit -m 'Add some AmazingFeature')

  4. Push to the branch (git push origin feature/AmazingFeature)

  5. Open a Pull Request

📄 License

This project is licensed under the MIT License - see the LICENSE file for details.


Available Tools

4 tools
fetch_htmlC

Fetch a website and return the content as HTML

Inputs: url (required), headers.

fetch_jsonC

Fetch a JSON file from a URL

Inputs: url (required), headers.

fetch_markdownC

Fetch a website and return the content as Markdown

Inputs: url (required), headers.

fetch_txtA

Fetch a website, return the content as plain text (no HTML)

Inputs: url (required), headers.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.6/5.0

    Scored across 4 tools

    Disambiguation5/5

    Each tool has a clearly distinct purpose based on the output format (HTML, JSON, Markdown, plain text), with no overlap in functionality. The descriptions explicitly differentiate them by content type, making tool selection straightforward for an agent.

    Naming Consistency5/5

    All tools follow a consistent verb_noun pattern with 'fetch_' prefix and suffix indicating the output format (e.g., fetch_html, fetch_json). The naming is perfectly uniform and predictable across all four tools.

    Tool Count5/5

    With 4 tools, this server is well-scoped for fetching content in different formats. Each tool earns its place by covering a distinct output type, and the count is neither too thin nor excessive for the domain of URL-based content retrieval.

    Completeness4/5

    The toolset covers the core fetching operations for common content types (HTML, JSON, Markdown, plain text), with no dead ends. A minor gap exists in not handling other formats like XML or binary data, but agents can work around this for most use cases.

    Maintenance

    ActivityInactive
    ResponsivenessOutdated data

    Related MCP Connectors

    Related MCP Servers