TheCrawler
by manchittlab
Open-source web scraper + LLM-powered structured extraction. PDF/DOCX, markdown, JSON-LD, microdata, commerce data, forms, 16 analytics-tracker detection. Structured errors with retryable flags. Adaptive Cheerio->Playwright. CLI, npm, REST API, and MCP server. AGPL-3.0.
📊 Score Breakdown
Overall = Security (30%) + Utility (30%) + Maintenance (25%) + Uniqueness (15%). Full methodology →
ℹ️ Details
Category
🔍 Search & Data Extraction
Ecosystem
MCP Server
Language
TypeScript
Pricing
Free
License
AGPL-3.0
Status
Active
Platforms
claude
📈 GitHub Signals
0
Stars
0
Forks
0
Commits (30d)
1
Open Issues
Last commit: 1 months ago
Similar Tools
View all Search & Data Extraction →SkillsIndex MCP
by SkillsIndex
Search and score 11,000+ AI agent tools (MCP servers, Claude skills, GPT actions) directly from Claude.
n8n
by n8n-io
Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.
Auto-claude-code-research-in-sleep
by wanshuiyin
ARIS ⚔️ (Auto-Research-In-Sleep) — Lightweight Markdown-only skills for autonomous ML research: cross-model review loops, idea discovery, and experiment automation. No framework, no lock-in — works wi
Brave Search MCP Server
by Anthropic
Web search via Brave Search API
Know before you install 📬
We score every tool 0-100 for security, maintenance and utility. Get the weekly shortlist of the highest-scored, vetted tools, plus an alert when a package you rely on goes stale. Free.
Data last verified: 1 weeks ago. See something wrong? Report it →