{
  "markdown": "# huoshui-fetch\n\nA dedicated web content fetching and conversion MCP (Model Context Protocol) server that provides tools for fetching, converting, and extracting data from web pages.\n\n## Features\n\n### Fetching Tools\n\n- **fetch_url**: Fetch content from URLs with customizable timeout, redirect handling, and user-agent\n- **fetch_with_headers**: Fetch URLs with custom headers for authenticated requests\n\n### Conversion Tools\n\n- **html_to_markdown_tool**: Convert HTML to clean Markdown format\n- **html_to_text_tool**: Extract plain text from HTML\n- **clean_html_tool**: Remove scripts/styles and sanitize HTML\n- **json_to_markdown_tool**: Convert JSON data to readable Markdown\n\n### Extraction Tools\n\n- **extract_article_tool**: Extract main article content using readability\n- **extract_links_tool**: Extract all links with filtering options\n- **extract_metadata_tool**: Extract page metadata (title, description, OG tags)\n- **extract_images_tool**: Extract images with size filtering\n- **extract_structured_data_tool**: Extract JSON-LD and microdata\n\n## Installation\n\nFrom MCP Registry (Recommended)\n\nThis server is available in the Model Context Protocol Registry. Install it using your MCP client.\n\nmcp-name: io.github.huoshuiai42/huoshui-fetch\n\n```bash\n# Using uv (recommended)\nuv sync\n\n# Or install from GitHub\npip install git+https://github.com/yourusername/huoshui-fetch.git\n```\n\n## Usage\n\n### Run with uvx (recommended for one-time use)\n\n```bash\n# From the repository\nuvx --from . huoshui-fetch\n\n# From GitHub (once published)\nuvx --from git+https://github.com/yourusername/huoshui-fetch.git huoshui-fetch\n```\n\n### Run directly\n\n```bash\n# Using uv\nuv run python -m huoshui_fetch\n\n# Or if installed\npython -m huoshui_fetch\n```\n\nThe server communicates via standard input/output, making it perfect for integration with Claude Desktop and other MCP-compatible clients.\n\n## Configuration for Claude Desktop\n\nAdd to your Claude Desktop configuration:\n\n```json\n{\n  \"mcpServers\": {\n    \"huoshui-fetch\": {\n      \"command\": \"uvx\",\n      \"args\": [\"--no-cache\", \"--from\", \".\", \"huoshui-fetch\"],\n      \"cwd\": \"/path/to/huoshui-fetch\"\n    }\n  }\n}\n```\n\nOr if installed from GitHub:\n\n```json\n{\n  \"mcpServers\": {\n    \"huoshui-fetch\": {\n      \"command\": \"uvx\",\n      \"args\": [\n        \"--from\",\n        \"git+https://github.com/yourusername/huoshui-fetch.git\",\n        \"huoshui-fetch\"\n      ]\n    }\n  }\n}\n```\n\n## Example Usage\n\nOnce configured, you can use the tools in Claude Desktop:\n\n```\n// Fetch a webpage\nfetch_url(\"https://example.com\")\n\n// Convert HTML to Markdown\nhtml_to_markdown_tool(\"<h1>Hello</h1><p>World</p>\")\n\n// Extract article content\nextract_article_tool(html_content, \"https://example.com/article\")\n```\n\n## Requirements\n\n- Python 3.11+\n- Dependencies listed in pyproject.toml\n\n## Development & Publishing\n\nThis project includes comprehensive automation for building and publishing to PyPI.\n\n### Automated Publishing Workflow\n\n```bash\n# Complete automated workflow (TestPyPI + PyPI)\nuv run python scripts/publish.py --include-pypi\n\n# TestPyPI only (recommended for testing)\nuv run python scripts/publish.py\n\n# Bump version and publish\nuv run python scripts/publish.py --version-bump patch --include-pypi\n```\n\n### Individual Commands\n\n```bash\n# Version management\nuv run python scripts/version_manager.py --check\nuv run python scripts/version_manager.py --bump patch\n\n# Setup PyPI credentials (first time)\nuv run python scripts/credentials_setup.py\n\n# Build package\nuv run python scripts/build.py\n\n# Run comprehensive tests\nuv run python scripts/test.py\n\n# Upload to PyPI\nuv run python scripts/upload.py\n```\n\n### Features\n\n- ✅ **Version Management**: Automatic synchronization across all files\n- ✅ **Quality Checks**: Ruff linting and MyPy type checking\n- ✅ **Build Automation**: Clean builds with validation\n- ✅ **Testing Suite**: Comprehensive package and functionality tests\n- ✅ **Publishing Workflow**: TestPyPI → PyPI using `uv publish` (supports `.pypirc` files)\n- ✅ **Error Recovery**: Built-in error handling and recovery options\n\nSee [PUBLISHING.md](PUBLISHING.md) for detailed documentation.\n\n## DXT Extension\n\nThis project supports DXT (Desktop Extensions) format for easy distribution and installation.\n\nTo build the DXT extension:\n\n```bash\npython build_dxt.py\n```\n\nThis will create a `huoshui-fetch-{version}.dxt` file that can be installed in compatible AI desktop applications.\n\n## License\n\nMIT\n",
  "bytes": 4418,
  "sha": "4db2f34a2373a4a3620928cd03eca806c1427c52af6bc1cdaec8e63c34515155",
  "repo_slug": "huoshuiai42/huoshui-fetch",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_huoshuiai42_huoshui_fetch_52abc0f8/readme"
}