Fetch MCP Server
# Fetch MCP Server
[](https://smithery.ai/server/@goswamig/fetch-mcp)
This MCP server provides functionality to fetch web content in various formats, including HTML, JSON, plain text, and Markdown.
## Components
### Tools
- **fetch_html**
- Fetch a website and return the content as HTML
- Input:
- `url` (string, required): URL of the website to fetch
- `headers` (object, optional): Custom headers to include in the request
- Returns the raw HTML content of the webpage
- **fetch_json**
- Fetch a JSON file from a URL
- Input:
- `url` (string, required): URL of the JSON to fetch
- `headers` (object, optional): Custom headers to include in the request
- Returns the parsed JSON content
- **fetch_txt**
- Fetch a website and return the content as plain text (no HTML)
- Input:
- `url` (string, required): URL of the website to fetch
- `headers` (object, optional): Custom headers to include in the request
- Returns the text content of the webpage with HTML tags, scripts, and styles removed
- **fetch_markdown**
- Fetch a website and return the content as Markdown
- Input:
- `url` (string, required): URL of the website to fetch
- `headers` (object, optional): Custom headers to include in the request
- Returns the content of the webpage converted to Markdown format
### Resources
This server does not provide any persistent resources. It's designed to fetch and transform web content on demand.
## Getting started
1. Clone the repository
2. Install dependencies: `npm install`
3. Build the server: `npm run build`
### Installing via Smithery
To install fetch-mcp for Claude Desktop automatically via [Smithery](https://smithery.ai/server/@goswamig/fetch-mcp):
```bash
npx -y @smithery/cli install @goswamig/fetch-mcp --client claude
```
### Usage
To use the server, you can run it directly:
```bash
npm start
```
This will start the Fetch MCP Server running on stdio.
### Usage with Desktop App
To integrate this server with a desktop app, add the following to your app's server configuration:
```json
{
"mcpServers": {
"fetch": {
"command": "node",
"args": [
"{ABSOLUTE PATH TO FILE HERE}/dist/index.js"
]
}
}
}
```
## Features
- Fetches web content using modern fetch API
- Supports custom headers for requests
- Provides content in multiple formats: HTML, JSON, plain text, and Markdown
- Uses JSDOM for HTML parsing and text extraction
- Uses TurndownService for HTML to Markdown conversion
## Development
- Run `npm run dev` to start the TypeScript compiler in watch mode
- Use `npm test` to run the test suite
## License
This project is licensed under the MIT License.
TDQS
Scored across 4 tools
The tools are mostly distinct, with each handling a different content type (HTML, JSON, Markdown, plain text). However, fetch_html and fetch_txt could be slightly confusing as both fetch websites, but their output formats (HTML vs. plain text) clarify the distinction. There is no significant overlap in purpose.
All tool names follow a consistent verb_noun pattern with 'fetch_' prefix and descriptive suffixes (html, json, markdown, txt). The naming is predictable and uniform, making it easy to understand the tool set at a glance.
With 4 tools, the count is reasonable for a fetch server focused on retrieving different content types. It is slightly lean but covers core use cases well. A few additional tools (e.g., for handling errors or metadata) might enhance it, but it's not incomplete.
The server covers fetching various content types, which aligns with its purpose. However, there are notable gaps: no tools for handling HTTP methods beyond GET (e.g., POST), error handling, or configuration (e.g., headers, timeouts). This limits advanced use cases but suffices for basic retrieval.