huoshui-fetch
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| fetch_urlA | Fetches content from a URL. Args: url: The URL to fetch timeout: Request timeout in seconds (default: 30) follow_redirects: Whether to follow redirects (default: True) user_agent: Custom user agent string (optional) Returns: Dictionary containing status_code, content, headers, encoding, and error (if any) |
| fetch_with_headersA | Fetches a URL with custom headers. Args: url: The URL to fetch headers: Dictionary of custom headers timeout: Request timeout in seconds (default: 30) Returns: Dictionary containing status_code, content, headers, encoding, and error (if any) |
| html_to_markdown_toolA | Converts HTML content to Markdown format. Args: html: HTML content to convert strip_tags: List of tags to strip (default: ['script', 'style', 'meta', 'link']) heading_style: Style for headings - "ATX" or "SETEXT" (default: "ATX") Returns: Dictionary with converted markdown content |
| html_to_text_toolA | Extracts plain text from HTML content. Args: html: HTML content to convert preserve_links: Whether to preserve link URLs in output (default: False) Returns: Dictionary with extracted text |
| clean_html_toolA | Cleans HTML by removing scripts, styles, and optionally limiting to allowed tags. Args: html: HTML content to clean allowed_tags: List of allowed tags (None = all tags except script/style) Returns: Dictionary with cleaned HTML |
| extract_article_toolA | Extracts the main article content from a web page. Args: html: HTML content url: Optional URL for resolving relative links Returns: Dictionary with title, content, text_content, excerpt, and short_title |
| extract_links_toolA | Extracts all links from HTML content. Args: html: HTML content base_url: Base URL for resolving relative links internal_only: Only return links from the same domain (default: False) Returns: Dictionary with list of links containing url, text, title, and rel attributes |
| extract_metadata_toolA | Extracts metadata from HTML including title, description, and Open Graph tags. Args: html: HTML content Returns: Dictionary containing title, description, keywords, author, open_graph, twitter_card, etc. |
| extract_images_toolA | Extracts all images from HTML content. Args: html: HTML content base_url: Base URL for resolving relative image URLs min_width: Minimum image width filter min_height: Minimum image height filter Returns: Dictionary with list of images containing src, alt, title, dimensions, etc. |
| extract_structured_data_toolA | Extracts structured data (JSON-LD, microdata) from HTML. Args: html: HTML content Returns: Dictionary containing json_ld and microdata if found |
| json_to_markdown_toolA | Converts JSON data to readable Markdown format. Args: json_data: JSON string to convert Returns: Dictionary with markdown representation of the JSON |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 11 tools
The fetch tools fetch_url and fetch_with_headers are highly similar, differing only in the ability to pass custom headers, which could lead to confusion about which to use. The extraction and conversion tools are all clearly distinct in their outputs, so mis-selection is unlikely for those.
Naming conventions are mixed: fetch_url and fetch_with_headers lack the '_tool' suffix that appears on all other tools, and there is no uniform prefix pattern. However, the 'extract_' and 'html_to_' groups are internally consistent, making the set readable overall.
With 11 tools, the server is well-scoped for a web fetching and processing utility. Each tool serves a distinct purpose in the pipeline, and the count is neither excessive nor too sparse for the stated functionality.
The tool surface covers the complete workflow of fetching, cleaning, converting, and extracting content from web pages. Minor gaps exist, such as the lack of cookie/session handling or CSS selector-based extraction, but these are not essential to the core purpose.