Best for
- Local LLM users with LM Studio or LibreChat
- Developers needing web search without API keys
- Users with recent tool-calling models like Qwen3 and Gemma 3
W
Web Search MCP Server
Community
Multi-engine web search and content extraction for local LLMs
GitHub source repository ↗
50FMRS · D
This server is feature-rich with multi-engine search and content extraction, but relies on Playwright browsers requiring resources. Works well with LM Studio and LibreChat, especially with recent models; older models may have issues.
A TypeScript MCP server providing API-key-free web search for local large language models. It uses a prioritized multi-engine strategy (Bing, Brave, DuckDuckGo), full-page content extraction, and Playwright browsers to deliver reliable web search results. Designed for local LLM clients like LM Studio and LibreChat, it offers three specialized tools and extensive environment configuration options.
Tools
full-web-search
Comprehensive search returning results with full page content.
get-web-search-summaries
Lightweight search returning only result snippets without content extraction.
get-single-web-page-content
Extracts main content from a specified URL, removing navigation and ads.
Setup
- Download the latest release zip from GitHub and extract it.
- In the extracted folder, run
npm install,npx playwright install, andnpm run build. - Configure the path to
dist/index.jsin your MCP client config.
claude_desktop_config.json
{
"mcpServers": {
"web-search": {
"command": "node",
"args": [
"/path/to/web-search-mcp/dist/index.js"
]
}
}
}
Fit and risk
Not for
- Those needing a stable proprietary search API
- Users with older Llama/Deepseek models that have tool-calling issues
- Environments with strict latency or resource constraints
Required permissions
- Local file system: run node/npm commands
- Network access: perform web searches and fetch pages
- Browser automation: download and run Playwright browsers
Risks and side effects
- Downloads browser binaries which may introduce security considerations
- Web content may contain unsafe scripts but extraction is handled
- Search engine behavior may be blocked or inconsistent
Troubleshooting
- If npm install fails, upgrade Node.js and npm
- If search fails, run `npx playwright install`
- For slow responses, set env vars like DEFAULT_TIMEOUT=4000, MAX_BROWSERS=1
- If content is truncated, set MAX_CONTENT_LENGTH
Use cases
Provide real-time web search to local LLMs
Get search summaries or full web page contents
Extract text from a known URL
Supported clients
LM StudioFull support
LibreChatFull support