pragmar/mcp-server-webcrawl

MCP server tailored to connecting web crawler data and archives

40
/ 100
Emerging

Implements a Python-based MCP server with boolean fulltext search (FTS5) across crawled web data, supporting seven crawler formats including ArchiveBox, HTTrack, Katana, and WARC archives. Provides field-specific filtering by HTTP status, resource type, and content, plus preset audit prompts for SEO, broken links, and performance analysis. Integrates directly with Claude Desktop via stdio transport to enable LLMs to autonomously query and analyze archived web content.

No Package No Dependents
Maintenance 6 / 25
Adoption 7 / 25
Maturity 9 / 25
Community 18 / 25

How are scores calculated?

Stars

37

Forks

14

Language

Python

License

Category

web-scraping-mcp

Last pushed

Dec 08, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/mcp/pragmar/mcp-server-webcrawl"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.