Web Researcher MCP
@zoharbabin
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
概览
What is Web Researcher MCP?
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.
How to use Web Researcher MCP?
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).
Key features of Web Researcher MCP
- Multiple specialized research tools in a single server
- Pluggable search backends with multi-provider routing and automatic fallback
- 4-tier content extraction (markdown, stealth HTTP, HTML, headless browser)
- Search lenses for domain-focused research (programming, news, legal, medical)
- Single static binary with optional Chromium for JS rendering
- Enterprise-ready: OAuth 2.1, multi-tenancy, rate limiting, audit logging
Use cases of Web Researcher MCP
- General web search with domain-focused search lenses
- Extract content from URLs including PDFs, DOCX, PPTX, and YouTube transcripts
- Combined search and extraction pipeline with quality scoring and deduplication
- Image and news search with filters and freshness controls
- Academic and patent search across scholarly databases and patent offices
FAQ from Web Researcher MCP
Which search providers are supported?
Google, Brave, Serper, SearXNG, and SearchAPI.io. Multi-provider routing with automatic fallback is available.
Do I need a Google API key?
Only if Google is your search provider. You can set SEARCH_ROUTING to use Brave, Serper, or other providers without Google keys.
Does it work with any MCP client?
Yes, it works with Claude Code, Claude Desktop, Cursor, and any MCP-compatible client over STDIO or HTTP/SSE transport.
What are the runtime requirements?
The server is a single static Go binary. For JavaScript-rendered pages, Chromium is auto-downloaded on first use.
Is there a Docker image?
Yes, available on Docker Hub (docker.io/zoharbabin/web-researcher-mcp) and GitHub Container Registry (ghcr.io/zoharbabin/web-researcher-mcp).
