
Read URL MCP
from takada-at
Extracts web content from a URL and converts it to clean Markdown format.
π₯π₯π₯β VerifiedFreeQuick setup
Read URL MCP
A Model Context Protocol (MCP) server that provides URL reading capabilities, extracting web content and converting it to clean Markdown format.
Features
- Fetch web content from HTTP/HTTPS URLs
- Extract main content using readability algorithm
- Convert HTML to clean Markdown format
- Configurable timeout and content size limits
MCP Setting
{
"mcpServers": {
"read_url_mcp": {
"command": "uv",
"args": [
"run",
"--directory",
"<directory>",
"read_url_mcp/mcp_server"
],
"env": {
"PYTHONPATH": "<directory>"
}
}
}
}Development
Code Quality
uv run ruff check # Lint code
uv run ruff format # Format code
uv run ruff check --fix # Auto-fix issuesDependencies
- mcp[cli] - MCP framework
- requests - HTTP client
- readability-lxml - Content extraction
- html2text - HTML to Markdown conversion
Copy & paste β that's it
uv installBefore it works, you'll need: PYTHONPATH
Installation
uv installUsage
Run the MCP server:
uv run python read_url_mcp/mcp_server.pyAvailable Tools
readURLMarkdown(url: str)- Fetches URL content and returns it as Markdown
Configuration
Server settings in mcp_server.py:
- Timeout: 30 seconds
- Max content length: 1MB
- User agent: my-mcp-tools/1.0
No common issues documented yet. If you hit a problem, the repository's GitHub Issues page is the best place to look.