web-researcher-mcp

⭐ If you're tired of AI making things up, and web-researcher-mcp helps you, give us a star ⭐ — it helps more teams discover the project.

Get started in 30 seconds

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

uv fetches the right prebuilt binary for your platform and runs it — no Go, no compile, no manual PATH. Point any MCP client at uvx web-researcher-mcp. Also works with uv tool install web-researcher-mcp or pip install web-researcher-mcp.

Python SDK

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)

macOS (Homebrew):

brew install zoharbabin/tap/web-researcher-mcp
claude mcp add --scope user web-researcher -- web-researcher-mcp

macOS / Linux (no package manager):

curl -fsSL https://raw.githubusercontent.com/zoharbabin/web-researcher-mcp/main/install.sh | sh

Windows (PowerShell):

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. The curl/PowerShell installers also register it with Claude Code automatically when the claude CLI is present; Homebrew installs the binary, so run the claude mcp add line above to connect it.

One-click install:

The Cursor / VS Code / LM Studio buttons install the zero-config uvx setup (your editor prompts to confirm before adding it; needs uv — see above). It runs DuckDuckGo web search with no API key — great to try instantly; image_search/news_search and richer providers need a key (2 min, see Configuration). Claude Desktop: download the .mcpb bundle for your platform and double-click it (Settings → Extensions), or use the uvx line above.

Using a different MCP client or want to pass API keys? See Connect to Your AI Assistant for the per-app config, and Configuration to 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.

---

Why does this exist?

Perplexity gets its citations wrong over a third of the time. It links to papers that don't exist, invents DOIs, and presents SEO spam with the same confidence as peer-reviewed research. ChatGPT's web search isn't much better — it can't tell a blog post from a court filing.

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 AI exactly which sources to search. We call these "search lenses" — curated lists of trusted sites for each field.

What you get	What that means for you
Search lenses — choose your sources by field	Your AI only sees the sites you trust (PubMed, SEC.gov, arXiv — not random blogs)
Research tools for every source type	Papers, patents, SEC filings, US court records, economic data, news, web pages, images, full-text reading, grounded answers with citations, structured extraction, and multi-step deep research
Always has a backup	Multiple search engines working together — if one has issues, the others pick up automatically
Reads full articles	Doesn't just give you snippets — extracts and reads entire pages, PDFs, Word docs, even YouTube transcripts and Hacker News threads
Real citations, formatted	Every source comes with a proper APA/MLA citation and a link that actually works
Your queries stay private	Runs on your machine — nobody sees what you're researching. Not us, not anyone.
Paper trail	Every search is logged so you can reproduce your research process months later

Works with Claude, Claude Desktop, Cursor, and any AI assistant that supports tool use.

Who uses this

• 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"

---

---

How It Compares

	web-researcher-mcp	Perplexity	Scite.ai	Elicit
You pick which sources are searched	Yes (built-in + custom lenses)	No	No	No
Makes up citations	Never — every link is real	~37% incorrect	Rare (journals only)	Rare
Works across all fields	Yes — legal, medical, news, patents, everything	Yes	Journals only	Papers only
Keeps your research private	Yes — runs on your machine	No (they see everything)	No	No
Works inside your existing AI (Claude, Cursor, etc.)	Yes	No (separate app)	Partially	No (separate app)
Can read full articles, not just snippets	Yes — pages, PDFs, Word docs, YouTube	No	No	Limited
Cost	Free forever (open source)	$20/mo	$20/mo	$10-49/mo

When to use what

• 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

---

What your AI can do with this

Tool	What it does
web_search	Search the web — optionally restricted to only the sources you trust via lenses
scrape_page	Read any URL in full — web pages, PDFs, Word docs, slideshows, YouTube transcripts, Hacker News threads (read natively via the HN API); supports mode: raw for verbatim, unsanitized source (e.g. inspecting JSON or HTML)
search_and_scrape	Search and then read the best results — with quality scoring to surface the most reliable sources
image_search	Find images by size, type, color, or format
news_search	Search recent news with date controls and source filtering
academic_search	Find real papers with real DOIs — authors, citation counts, open-access links
paper_fulltext	Fetch a paper's full text in one call from its DOI, Semantic Scholar ID, or URL — no need to chain academic_search then scrape_page
citation_graph	Walk a paper's citation neighborhood — works it cites and works that cite it, with intent/influence signals
patent_search	Search patent offices (US, Europe, international) with classification codes
filing_search	Search SEC EDGAR for US public-company filings (10-K, 10-Q, 8-K, …) — or pull structured XBRL company facts
legal_search	Search US court opinions and dockets via CourtListener — real cases with real citations
econ_search	Look up economic data — World Bank global development indicators, OECD economic indicators, Eurostat European statistics (all keyless), and FRED US macro series (GDP, CPI, unemployment, rates; requires FRED_API_KEY)
clinical_search	Search ClinicalTrials.gov — clinical-trial registrations with status, phase, sponsor, and whether results are posted (discovery, not medical advice)
monarch_search	Query the Monarch Initiative biomedical knowledge graph — rank diseases and genes by phenotype similarity, look up disease/gene/phenotype entities, traverse gene-disease-phenotype associations
awesome_list_search	Search the ecosyste.ms Awesome API for community-curated "awesome-*" lists on a GitHub topic — structured, filterable coverage (stars, curated-entry count, topics) beyond free-text search
local_search	Search for physical places (restaurants, shops, services, points of interest) by local intent query — structured POI details and descriptions. Requires BRAVE_API_KEY
brand_research	Research a company's complete brand identity — colors (hex), logos, typography, tone of voice, and social handles — from any domain or company name. Returns structured JSON for AI content generation. No API key required; BrandFetch key optional for richer data
company_recon	OSINT company reconnaissance — Certificate Transparency log SANs, Wayback Machine historical URL inventory, derived subdomains, and a web-search company summary. Each phase fails soft and is independently selectable
verify_citation	Check a citation before you rely on it — does it exist, match a real record, and is it retracted or a dead link? Evidence, not a verdict
audit_bibliography	Audit a whole reference list in one pass — paste a CSL-JSON/RIS/BibTeX file (or a session) and get per-entry + corpus-level flags for retracted, dead-link, and unverifiable citations
verify_recommendation	Audit an AI-generated recommendation list (listicle, product ranking) for self-promotion, author conflicts of interest, domain reputation, and dead links — catches GEO-gamed picks. Evidence, not a verdict
archive_source	Capture a fresh Internet Archive (Wayback Machine) snapshot of a URL via Save Page Now so a cited source stays verifiable if the page later changes or disappears — returns snapshot URL + timestamp (write tool)
sequential_search	Multi-step deep research — your AI remembers what it already found and builds on it
get_research_session	Recover a research session after context loss — picks up right where you left off
research_export	Export a research session as a shareable report (markdown or JSON), with full per-step provenance
format_bibliography	Turn collected sources into a formatted bibliography — APA, MLA, BibTeX, RIS, or CSL-JSON (Zotero/EndNote/Mendeley-ready)
research_panel	Ask the same question to a panel of independently configured LLMs and compare answers — consensus, contradictions, and model-unique points, computed deterministically, never smoothed over by an arbiter model

Most tools above are always available. A few activate only when the right provider or config is present: citation_graph and research_panel require at least one configured backing provider; filing_search requires EDGAR_CONTACT_EMAIL; local_search requires BRAVE_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 — see docs/TOOLS.md for the authoritative, CI-verified tool list and full schemas.

Ready-made research templates

The server also ships guided prompt templates your 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:

Template	What it guides your AI to do
comprehensive-research	Run a structured, multi-step deep dive on a topic
fact-check	Verify a claim against multiple independent sources
competitive-analysis	Size up a company and its market (news, patents, web)
literature-review	Systematically review academic literature on a topic
brand-guidelines	Research a brand and produce use-case-specific creative direction (landing page, email, video brief) — calls brand_research and interprets the structured JSON for you
company-recon	Deep OSINT reconnaissance on a company — maps infrastructure, filings, personnel, and public footprint
curriculum-research	Research a subject's syllabus coverage, institutional climate, and academic-freedom context — calls web_search with the curriculum lens

In most AI apps these show up wherever you pick a prompt or "/" command. The server exposes live status 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. See docs/DEPLOYMENT.md for the full list.

---

Quick Start

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)

macOS / Linux:

curl -fsSL https://raw.githubusercontent.com/zoharbabin/web-researcher-mcp/main/install.sh | sh

Windows (PowerShell):

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

AUR (Arch Linux):

# 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

Nix / NixOS:

# 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.nix for NixOS module usage.

Continue.dev:
Add to your Continue ~/.continue/config.json:

{
  "mcpServers": {
    "web-researcher": {
      "command": "uvx",
      "args": ["web-researcher-mcp"]
    }
  }
}

Or copy packaging/continue/config.json as a starting point.

WinGet (Windows):

winget install zoharbabin.web-researcher-mcp

Scoop (Windows):

scoop bucket add zoharbabin https://github.com/zoharbabin/scoop-bucket
scoop install web-researcher-mcp

Chocolatey (Windows):

choco install web-researcher-mcp

Homebrew Cask (macOS — Developer ID-signed + notarized binary):

brew install --cask zoharbabin/tap/web-researcher-mcp

The cask ships the notarized darwin binary (Gatekeeper-clean). Most users want the formula above (brew install zoharbabin/tap/web-researcher-mcp), which the bare name resolves to; pass --cask explicitly for the notarized artifact.

Go install (if you have Go):

go install github.com/zoharbabin/web-researcher-mcp/cmd/web-researcher-mcp@latest
claude mcp add --scope user web-researcher -- web-researcher-mcp

Docker:

# STDIO mode needs -i so the container's stdin stays attached for MCP JSON-RPC
docker run -i --rm \
           -e GOOGLE_CUSTOM_SEARCH_API_KEY=YOUR_KEY \
           -e GOOGLE_CUSTOM_SEARCH_ID=YOUR_CX \
           docker.io/zoharbabin/web-researcher-mcp:latest

Build from source:

git clone https://github.com/zoharbabin/web-researcher-mcp.git
cd web-researcher-mcp
go build -o web-researcher-mcp ./cmd/web-researcher-mcp

Connect to Your AI Assistant

The install script registers with Claude Code automatically. For other apps, add to your AI's config file:

{
  "mcpServers": {
    "web-researcher": {
      "command": "web-researcher-mcp",
      "env": {
        "GOOGLE_CUSTOM_SEARCH_API_KEY": "YOUR_GOOGLE_API_KEY",
        "GOOGLE_CUSTOM_SEARCH_ID": "YOUR_SEARCH_ENGINE_ID"
      }
    }
  }
}

Any provider works — pick one and set its key. For example, Brave (no Google keys needed):

{
  "mcpServers": {
    "web-researcher": {
      "command": "web-researcher-mcp",
      "env": {
        "SEARCH_PROVIDER": "brave",
        "BRAVE_API_KEY": "YOUR_BRAVE_API_KEY"
      }
    }
  }
}

Swap in any provider from the Configuration table by setting SEARCH_PROVIDER and that provider's key. Done — your AI assistant now has access to all research tools.

---

Configuration

No API key required. DuckDuckGo is the built-in zero-config fallback — install and go. To raise result quality and unlock image/news search, add any one of the providers below. They're all optional and interchangeable — pick whichever you already use or prefer; the server treats them equally.

Search providers

Set SEARCH_PROVIDER=<name> and supply that provider's key. Every provider works with search lenses, and any of them can be combined for automatic failover (see Search Providers).