Web Researcher MCP
About
Production-grade MCP server for web search, content extraction, and multi-source research — 8 tools, 5 search providers with automatic failover, 4-tier scraping pipeline. Single Go binary.
Details
- Author
- zoharbabin
- Categories
- Search, Knowledge Base, Other
Jump to
Option 2: One-command install (any OS — no dev tools needed)
curl -fsSL https://raw.githubusercontent.com/zoharbabin/web-researcher-mcp/main/install.sh | sh
powershell -ExecutionPolicy Bypass -c "irm https://raw.githubusercontent.com/zoharbabin/web-researcher-mcp/main/install.ps1 | iex"
Downloads the binary, verifies its SHA-256 checksum against the signed release, puts it on your PATH, and registers it with Claude Code if installed. Customize the install location:
INSTALL_DIR=/opt/tools curl -fsSL https://raw.githubusercontent.com/zoharbabin/web-researcher-mcp/main/install.sh | sh
# Using any AUR helper (yay, paru, etc.) yay -S web-researcher-mcp
Or manually:git clone https://aur.archlinux.org/web-researcher-mcp.git && cd web-researcher-mcp && makepkg -si
# Run without installing nix run github:zoharbabin/web-researcher-mcp # Add to your flake inputs nix profile install github:zoharbabin/web-researcher-mcp
See](https://github.com/zoharbabin/web-researcher-mcp/blob/HEAD/docs/DEPLOYMENT.md#mcp-resources--prompts)[packaging/nix/flake.nixfor NixOS module usage.
Continue.dev:
Add to your Continue~/.continue/config.json:
…
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 can trust,
no made up closed garden pre-synthesized results.
⭐ If you're tired of AI making things up, andweb-researcher-mcphelps you, give us a star ⭐ — it helps more teams discover the project.
Python users —uvx(no compile, any OS):
# One-time: install uv (skip if you already have it) curl -LsSf https://astral.sh/uv/install.sh | sh # macOS/Linux (Windows: winget install astral-sh.uv) claude mcp add --scope user web-researcher -- uvx web-researcher-mcp
from web_researcher_mcp import WebResearcherClient async with WebResearcherClient() as client: response = await client.web_search("CRISPR off-target effects 2024", num_results=5) for r in response.results: verified = await client.verify_citation(r.url) print(r.title, "—", "✓" if verified.exists else "?")
Full documentation:docs/PYTHON_CLIENT.md
Sync wrapper (for scripts and notebooks that don't use async):
with WebResearcherClient.sync() as client: response = client.web_search("climate change 2024") print(response.results[0].title)
brew install zoharbabin/tap/web-researcher-mcp claude mcp add --scope user web-researcher -- web-researcher-mcp
curl -fsSL https://raw.githubusercontent.com/zoharbabin/web-researcher-mcp/main/install.sh | sh
powershell -ExecutionPolicy Bypass -c "irm https://raw.githubusercontent.com/zoharbabin/web-researcher-mcp/main/install.ps1 | iex"
No dev tools needed — every method ships the same signed binary (the PyPI wheels vendor it; the others download it and verify its checksum) and puts it on your PATH. Thecurl/PowerShell installers also register it with Claude Code automatically when theclaudeCLI is present; Homebrew installs the binary, so run theclaude mcp addline above to connect it.
The Cursor / VS Code / LM Studio buttons install the zero-configuvxsetup (your editor prompts to confirm before adding it; needsuv— see above). It runsDuckDuckGo web search with no API key— great to try instantly;image_search/news_searchand richer providers need a key (2 min, seeConfiguration).Claude Desktop:download the.mcpbbundlefor your platform and double-click it (Settings → Extensions), or use theuvxline above.
Using a different MCP clientor want to pass API keys? SeeConnect to Your AI Assistantfor the per-app config, andConfigurationto pick a search provider.
Your AI can now search the web, read full articles, find academic papers, look up patents, and run multi-step research — only from sources you pick.
If your work gets cited, published, submitted to a court, or shown to a client — you can't afford "probably real" sources.
This tool fixes the root cause:instead of searching the entire web and hoping, you tell your AIexactly which sources to search. We call these "search lenses" — curated lists of trusted sites for each field.
Works with Claude, Claude Desktop, Cursor, and any AI assistant that supports tool use.
- Academic researchers— "I need a literature review with real DOIs, not made-up citations"
- Business analysts— "My deliverable needs sources a client can actually click and verify"
- Lawyers— "If I cite a case that doesn't exist, I get fined $50,000"
- Journalists— "I need to cross-check government records and court filings, not Perplexity summaries"
- Medical researchers— "Clinical decisions based on a health blog could hurt someone"
- Graduate students— "I spent 3 hours tracking down a citation my AI invented"
- Enterprise teams— "Our competitive research can't go through a third party's servers"
- Perplexity— Quick casual lookups where you don't need to cite your sources
- Scite.ai / Elicit— Browsing a specific database of academic papers
- web-researcher-mcp— Anything where your reputation is attached to the research: client work, court filings, publications, grant proposals, medical decisions, journalism
- Claude built-in search— Quick one-off lookups mid-conversation
Most tools above are always available. A few activate only when the right provider or config is present:citation_graphandresearch_panelrequire at least one configured backing provider;filing_searchrequiresEDGAR_CONTACT_EMAIL;local_searchrequiresBRAVE_API_KEY. Operators can also enable opt-in, consent-gated tools (per-user analytics, long-term memory, shared workspaces, saved-query monitoring) that appear only when their feature is turned on — seedocs/TOOLS.mdfor the authoritative, CI-verified tool list and full schemas.
The server also ships guidedprompt templatesyour AI assistant can pull in with one click — they walk it through a proven, multi-step process so you don't have to spell out every instruction:
In most AI apps these show up wherever you pick a prompt or "/" command. The server exposes livestatus resources(stats://tools,stats://sessions,stats://rate-limits,stats://providers), a lens catalog (lenses://catalog), diagnostics (diagnostics://errors/recent,diagnostics://health), and a large-payload artifact store (research://artifact/{id}) so you — or your AI — can check usage, limits, and which providers are active. Seedocs/DEPLOYMENT.mdfor the full list.
Option 1: Homebrew (macOS / Linux — recommended)
brew install zoharbabin/tap/web-researcher-mcp claude mcp add --scope user web-researcher -- web-researcher-mcp
Homebrew handles trust, updates, and PATH for you — no signing warnings.
Option 2: One-command install (any OS — no dev tools needed)
curl -fsSL https://raw.githubusercontent.com/zoharbabin/web-researcher-mcp/main/install.sh | sh
powershell -ExecutionPolicy Bypass -c "irm https://raw.githubusercontent.com/zoharbabin/web-researcher-mcp/main/install.ps1 | iex"
Downloads the binary, verifies its SHA-256 checksum against the signed release, puts it on your PATH, and registers it with Claude Code if installed. Customize the install location:
INSTALL_DIR=/opt/tools curl -fsSL https://raw.githubusercontent.com/zoharbabin/web-researcher-mcp/main/install.sh | sh
# Using any AUR helper (yay, paru, etc.) yay -S web-researcher-mcp
Or manually:git clone https://aur.archlinux.org/web-researcher-mcp.git && cd web-researcher-mcp && makepkg -si
# Run without installing nix run github:zoharbabin/web-researcher-mcp # Add to your flake inputs nix profile install github:zoharbabin/web-researcher-mcp
See[packaging/nix/flake.nixfor NixOS module usage.
Continue.dev:
Add to your Continue~/.continue/config.json:
…
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
