Scraper
A web scraping MCP server built by Carrotly AI that provides four core tools for extracting content from websites: raw HTML scraping, markdown conversion, plain text extraction, and link discovery. Built with FastMCP and featuring an extensible provider architecture (currently using requests with exponential backoff retry logic), it supports both single URL and batch operations with configurable concurrency, intelligent disk-based caching with TTL management, CSS selector filtering for targeted content extraction, and optional ScrapeOps proxy integration for JavaScript rendering and anti-bot bypass. The implementation includes a web dashboard for monitoring and testing, comprehensive error handling with graceful degradation, and Docker deployment support, making it useful for research automation, content analysis workflows, and building web scraping pipelines with built-in resilience and caching.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately. Last scanned 2026-09-19.
Scan details: Circle-IR · 2026-09-19 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- cloud-infra
- Source
- PulseMCP
- Repository
- github.com/cotdp/scraper-mcp
- Author type
- human
- Last scanned
- 2026-09-19
- Updated
- 2026-09-19
Use via MCP
Resolve Scraper from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp--scope user for --scope project to commit it to .mcp.json.