How to add Web Search MCP Server to Claude Desktop
Locally hosted multi-engine web search and page content extraction for local LLMs — no API keys required. Paste the config into ~/Library/Application Support/Claude/claude_desktop_config.json and restart Claude Desktop.
Last updated June 14, 2026 · 980★ · stdio · no auth
Claude Desktop config for Web Search MCP Server
npm install && npx playwright install && npm run build{
"mcpServers": {
"web-search-mcp-server": {
"command": "node",
"args": [
"/path/to/extracted/web-search-mcp/dist/index.js"
]
}
}
}Setup steps
- 1Open Claude Desktop → Settings → Developer → Edit Config (this opens ~/Library/Application Support/Claude/claude_desktop_config.json).
- 2Paste the Web Search MCP Server config below under the top-level "mcpServers" key.
- 3Fill in any placeholder secrets (API keys, paths) in the snippet.
- 4Save the file, then fully quit and reopen Claude Desktop.
- 5Open a chat and confirm Web Search MCP Server's tools appear under the 🔌 tools menu.
Before you start
- Node.js 18.0.0 or higher
- npm 8.0.0 or higher
- Playwright browsers installed via 'npx playwright install'
What Web Search MCP Server can do in Claude Desktop
full-web-searchMain tool. Takes a query and an optional number of results (1-10, default 5), performs a multi-engine web search (Bing, then Brave, then DuckDuckGo), fetches full page content from each result URL with concurrent processing, and returns structured data with search results and extracted content. Includes HTTP/2 error recovery and reduced timeouts.
get-web-search-summariesLightweight alternative. Takes a query and an optional number of results (1-10, default 5), performs the same optimised multi-engine search, and returns only the search result snippets/descriptions without following links to extract full page content.
get-single-web-page-contentUtility tool. Takes a single URL (and optional maxContentLength), follows it, and extracts the main page content while removing navigation, ads, and other non-content elements. Useful for getting detailed content from a known webpage.
Security
Runs locally with no API keys. Performs browser automation and HTTP requests to third-party search engines and arbitrary result URLs; some networks block browser automation. Content length is capped via MAX_CONTENT_LENGTH (default 500000 characters).
Web Search MCP Server + Claude Desktop FAQ
Where is the Claude Desktop config file?
Claude Desktop reads MCP servers from ~/Library/Application Support/Claude/claude_desktop_config.json. Paste the Web Search MCP Server config there under the "mcpServers" key and restart the client.
Is Web Search MCP Server safe to use with Claude Desktop?
Runs locally with no API keys. Performs browser automation and HTTP requests to third-party search engines and arbitrary result URLs; some networks block browser automation. Content length is capped via MAX_CONTENT_LENGTH (default 500000 characters).
Do I need any API keys?
No. The server uses direct connections to search engines and web pages (browser automation via Playwright plus axios HTTP requests), so no API keys are required.
Which MCP clients does it support?
It has been developed and tested with LM Studio and LibreChat. The README notes it has not been tested with other MCP clients.
Which models work best?
Recent models designated for tool use work best; Qwen3 and Gemma 3 give the best results. Llama 3.2, recent Llama 3.1, and recent Deepseek R1 (e.g. 0528) also work, while older Llama and Deepseek R1 versions may not.