GetWeb
MCP-GetWeb server by Ivan Mezentsev provides AI assistants with comprehensive web search and content extraction capabilities through seven specialized tools integrating DuckDuckGo HTML scraping, Google Programmable Search Engine API, Felo AI search, Jina Reader API, and custom URL fetching with content extraction controls. Built in Rust with extensive caching, user agent rotation, and robust error handling, the implementation offers both basic web search across multiple engines and advanced content processing including metadata extraction, HTML-to-Markdown conversion, and configurable text extraction with main content detection and tag filtering. Designed for AI applications requiring reliable web research capabilities, real-time information retrieval, and flexible content processing workflows where multiple search engines and extraction methods provide redundancy and specialized functionality for different types of web content.
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
- search
- Source
- PulseMCP
- Repository
- github.com/ivan-mezentsev/mcp-getweb
- Author type
- human
- Last scanned
- 2026-09-19
- Updated
- 2026-09-19
Use via MCP
Resolve GetWeb 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.