MCP Server Fetch Typescript

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

typescript

0

GitHub Stars

typescript

Language

7 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": {
    "mcp-mirror-tatn_mcp-server-fetch-typescript": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-server-fetch-typescript"
      ]
    }
  }
}

This MCP Server lets you fetch and convert web content through a versatile API. It supports retrieving raw text, rendering fully rendered HTML, converting content to Markdown, and extracting clean Markdown summaries for articles or blogs. You can integrate it with an MCP client to automate data extraction, archiving, or documentation workflows.

How to use

You can connect your MCP client to this server using one of the supported execution methods. The server exposes endpoints that let you fetch raw text, get rendered HTML, convert pages to Markdown, or produce focused Markdown summaries. Use the method that best fits your use case: quick text extraction, SPA rendering needs, or structured content for archives and documentation.

How to install

Prerequisites: Node.js and npm must be installed on your system.

Option A: Install as a global package and run with npx.

npm install -g mcp-server-fetch-typescript

Option B: Install as a project dependency, then build and run.

npm install mcp-server-fetch-typescript

Build and start your local instance.

# From the project root after cloning
npm install
npm run build

Running via npx (no local build required) can be done with this command.

npx -y mcp-server-fetch-typescript

If you prefer to run a built local copy, start the server with Node and the built entrypoint.

/nodepath/to/mcp-server-fetch-typescript/build/index.js

Additional notes

For debugging or development, you can use the inspector tool to attach to the MCP server process.

Available tools

get_raw_text

Retrieve raw text content directly from URLs. Returns unprocessed text suitable for JSON, XML, CSV, TSV, or plain text resources.

get_rendered_html

Fetch fully rendered HTML content by executing JavaScript in a headless browser, producing content as seen by users.

get_markdown

Convert web content to Markdown format, preserving structure, tables, and definition lists for documentation or archiving.

get_markdown_summary

Extract and convert the main content to clean Markdown, automatically removing navigation and headers for focused articles.