Which search providers are supported?
Google, Brave, Serper, SearXNG, and SearchAPI.io. Multi-provider routing with automatic fallback is available.

@zoharbabin
基本信息
Your AI research assistant that cites real sources and stays honest. Search the entire web or narrow it down to just the sites you trust; medical journals, court databases, news outlets, academic papers. Analyze the full source, not just snippets. Links that work, citations you c
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"web-researcher": {
"command": "web-researcher-mcp",
"args": [],
"env": {
"GOOGLE_CUSTOM_SEARCH_API_KEY": "<YOUR_KEY>",
"GOOGLE_CUSTOM_SEARCH_ID": "<YOUR_CX>",
"SEARCH_PROVIDER": "google"
}
}
}
}General web search with optional search lenses for domain-focused results
Extract content from any URL -- web pages, PDFs, DOCX, PPTX, YouTube transcripts (3-strategy fallback)
Combined search + extraction pipeline with quality scoring and deduplication
Search for images with size, type, color, and file format filters
Search news sources with freshness controls and source filtering
Search peer-reviewed papers across arXiv, PubMed, IEEE, Nature, Springer, and other scholarly databases
Search patent databases with CPC classification, strict office filtering (US/EP/WO/JP/CN/KR)
Multi-step research tracking with session state for iterative investigation
Web Researcher MCP is a production-grade MCP server that gives AI assistants the ability to search the web, extract content, and conduct multi-source research. It works with any MCP-compatible client such as Claude Code, Claude Desktop, and Cursor.
Install via Go (go install github.com/zoharbabin/web-researcher-mcp/cmd/web-researcher-mcp@latest), download a prebuilt binary, run a Docker container, or build from source. Then configure search provider credentials (e.g., Google, Brave) in environment variables and add the server to your MCP client configuration (e.g., ~/.claude/settings.json).
Google, Brave, Serper, SearXNG, and SearchAPI.io. Multi-provider routing with automatic fallback is available.
Only if Google is your search provider. You can set `SEARCH_ROUTING` to use Brave, Serper, or other providers without Google keys.
Yes, it works with Claude Code, Claude Desktop, Cursor, and any MCP-compatible client over STDIO or HTTP/SSE transport.
The server is a single static Go binary. For JavaScript-rendered pages, Chromium is auto-downloaded on first use.
Yes, available on Docker Hub (`docker.io/zoharbabin/web-researcher-mcp`) and GitHub Container Registry (`ghcr.io/zoharbabin/web-researcher-mcp`).

Handl speaks the Model Context Protocol. Your whole billing operation — projects, invoices, clients, reports, approvals — as tools any AI assistant can call, inside your autonomy rules.

Yuppsy MCP: build and publish real estate websites from your AI assistant. Yuppsy lets your AI assistant create live websites for real estate agents and individual property listings. You don't need a designer or any code

Model Context Protocol Servers
YC (S26) | Open Computer History | Continuously record your company computer work, map your workflows, help you find work worth automating, and power your agents' context

Run advanced phishing, voice phishing, deepfake fraud simulations, and cybersecurity awareness training from your AI assistant.
评论