Open Web Search
This MCP server provides AI assistants with web search capabilities across multiple search engines including Bing, Baidu, Brave, DuckDuckGo, and Exa, plus specialized content extraction from Chinese platforms like CSDN, Zhihu, and LinuxDo. Built using TypeScript with axios for HTTP requests, cheerio for HTML parsing, and JSDOM for content processing, it features configurable search engine selection, site-specific search filtering, and dedicated article content extraction that bypasses anti-bot measures using realistic browser headers and cookies. The implementation includes comprehensive error handling, result pagination, and supports both general web search and targeted content retrieval from technical forums and knowledge platforms, making it valuable for research workflows, content analysis, and building AI assistants that need programmatic access to Chinese technical content and general web search results without manual browsing.
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
- browser-automation
- Source
- PulseMCP
- Repository
- github.com/aas-ee/open-websearch
- Author type
- human
- Last scanned
- 2026-09-19
- Updated
- 2026-09-19
Use via MCP
Resolve Open 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.