Web Search
A web search MCP server built by hexdecimal16 that performs Google searches and crawls content from the top 5 non-social media results using crawl4ai for content extraction. The implementation provides a single web_search tool that takes a query, identifies relevant search results, and returns the crawled content as a consolidated string, with built-in filtering to exclude social media platforms and focus on substantive web content. Designed for AI assistants that need access to current web information for research, fact-checking, or content discovery workflows where users require comprehensive search results beyond what's available in training data.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately.
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- browser-automation
- Source
- PulseMCP
- Repository
- github.com/hexdecimal16/web-search-mcp
- Author type
- human
- Updated
- 2026-04-25
Use via MCP
Resolve Web Search 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.