Open-WebSearch
Open-Websearch provides an MCP server that enables live web searching and content retrieval across multiple search engines (Bing, Baidu, DuckDuckGo, Brave, Exa, and others) without requiring API keys or authentication. The server offers structured search results with titles, URLs, and descriptions, along with content fetching capabilities for specific sources like CSDN, GitHub, and generic web pages, with support for HTTP proxy configuration. It solves the problem of integrating real-time web search into AI applications and agents while maintaining flexibility through multiple deployment options: MCP integration with clients like Claude Desktop, CLI for direct terminal usage, and a local daemon for reusable HTTP-based access.
- GitHub stars
- 1.2K
- tools
- 6
- last updated
- Jan 29, 2026
Tools
6 toolsPublic tool metadata for what this MCP can expose to an agent.
searchWeb search using multi-engine results, returning structured results with titles, URLs, and descriptions.
Web search using multi-engine results, returning structured results with titles, URLs, and descriptions.
No parameter schema in public metadata yet.
fetchLinuxDoArticleUsed to fetch complete content of Linux.do forum articles.
Used to fetch complete content of Linux.do forum articles.
No parameter schema in public metadata yet.
fetchCsdnArticleUsed to fetch complete content of CSDN blog articles.
Used to fetch complete content of CSDN blog articles.
No parameter schema in public metadata yet.
fetchGithubReadmeUsed to fetch README content from GitHub repositories.
Used to fetch README content from GitHub repositories.
No parameter schema in public metadata yet.
fetchJuejinArticleUsed to fetch complete content of Juejin articles.
Used to fetch complete content of Juejin articles.
No parameter schema in public metadata yet.
fetchWebContentFetch content directly from public HTTP(S) links, including Markdown files, ordinary pages, and JavaScript-rendered pages when Playwright is configured.
Fetch content directly from public HTTP(S) links, including Markdown files, ordinary pages, and JavaScript-rendered pages when Playwright is configured.
No parameter schema in public metadata yet.
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageReadme
open-websearch provides an MCP server, CLI, and local daemon, and can also be paired with skill-guided agent workflows for live web search and content retrieval without API keys.
Sponsor
Details
- Repository
- github.com/aas-ee/open-websearch
- Categories
- Developer Tools, Search & Web Crawling
Related Developer Tools MCP servers
View all
Octocode MCP - AI Context Platformbgauryy/octocode-mcpAI code research platform. Search, analyze, and extract insights from any GitHub repository.863stars
Context Syncintina47/context-syncUniversal AI Memory - Sync context across Claude, VsCode, Cursor, Continue, Windsurf, Zed & more165stars
DOMShellapireno/domshellDrive Chrome with filesystem commands (ls, cd, grep, click, type). One MCP tool, multi-agent.59stars
Airtable User MCPautomations-project/vscode-airtable-formulaManage Airtable bases: schema, field CRUD, views, formula validation, extensions0stars
Neverinfamous Memory Journal Mcpneverinfamous/memory-journal-mcpA MCP server built for developers enabling Git based project management with project and personal…17stars
Instagitinstalabsai/instagitMCP server for Instagit — AI-powered Git repository analysis for coding agents17stars