home / mcp / mcp-server-fetch-typescript mcp server

mcp-server-fetch-typescript MCP Server

Provides web content fetching and conversion capabilities with raw text, rendered HTML, and Markdown outputs.

Installation

Add the following to your MCP client configuration file.

Configuration

{
  "mcpServers": {
    "tatn-mcp-server-fetch-typescript": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-server-fetch-typescript"
      ]
    }
  }
}

You deploy the MCP server fetch-typescript to retrieve and convert web content. It gives you raw text, fully rendered HTML, and Markdown outputs from URLs, enabling fast data extraction, documentation archiving, or article analysis in your automation pipelines.

How to use

You run the server locally or remotely and connect to it through an MCP client to fetch content. You can choose between raw text, rendered HTML, or Markdown formats depending on your task: raw text for JSON/XML/CSV, rendered HTML for dynamic pages, and Markdown for documentation-friendly output.

How to install

Prerequisites: You need Node.js and npm installed on your machine.

Install the MCP server package globally so you can run it from anywhere.

npm install -g mcp-server-fetch-typescript

Alternatively, install it as a project dependency in your project.

npm install mcp-server-fetch-typescript

Usage variants to run the MCP server locally are shown below. Choose one path that matches your setup.

# Option 1: Run directly with npx (temporary execution)
npx -y mcp-server-fetch-typescript

# Option 2: Build from source and run the built index
git clone https://github.com/tatn/mcp-server-fetch-typescript.git
cd mcp-server-fetch-typescript
npm install
npm run build

# Start from the built file
node /path/to/mcp-server-fetch-typescript/build/index.js

Additional notes

To debug the MCP server during development, you can use the inspector tool with either npm or node, as shown below.

npx @modelcontextprotocol/inspector npx -y mcp-server-fetch-typescript
```
```
npx @modelcontextprotocol/inspector node /path/to/mcp-server-fetch-typescript/build/index.js

Available tools

get_raw_text

Retrieve raw text content directly from URLs. Returns unprocessed text content without browser rendering, suitable for JSON, XML, CSV, TSV, or plain text files.

get_rendered_html

Fetch fully rendered HTML content. Executes JavaScript using a headless browser and returns complete HTML content.

get_markdown

Convert web content to Markdown format. Preserves structure, including tables and definition lists.

get_markdown_summary

Extract and convert the main content to Markdown, removing navigation, headers, and footers for clean article or blog extraction.