# BaektotheFuture98/Python Crawling MCP

Source: https://glimind.com/server/glama%2Fbaektothefuture98%2Fpython-crawling-mcp
Registry id: `glama/baektothefuture98/python-crawling-mcp`
Status: unknown

## Tools (10)

- `configure_crawl_target`: Creates or updates a crawl target configuration for periodic crawling.
- `crawl_site`: Crawls a site starting from a given URL with configurable limits and filters.
- `get_article`: Returns the full content of a single article by ID.
- `get_crawl_status`: Returns recent worker job aggregates for a crawl target or all targets.
- `get_recent_article_changes`: Returns recent article changes with metadata but not content.
- `list_crawl_targets`: Lists crawl targets with their configuration and schedule status.
- `list_supported_sites`: Lists registered domains, authentication adapter names, and extractor names.
- `run_crawl_target`: Immediately runs a registered crawl target once and returns aggregate counts.
- `scrape_page`: Scrapes a single public page or an authenticated page using a registered auth profile.
- `validate_session`: Validates the stored session for a given auth profile by checking authentication markers on the site.

Measured by Glimind (https://glimind.com): MCP handshake + tool list only, no tool is ever called. CC BY 4.0.