Web Research MCP Server

● Active

io.github.shukoilab/web-research-mcp

Stealth Google Search and token-efficient web content extraction with undetected browser automation.

Connect this server

One click to install, or copy the config below. Suits: Claude Desktop · Cursor.

Add to Cursor Add to VS CodeClaude Desktop / Claude Code: paste the config below.

Or add it manually — claude_desktop_config.json (Claude Desktop) or .cursor/mcp.json (Cursor):

{
  "mcpServers": {
    "web-research-mcp": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "ghcr.io/shukoilab/web-research-mcp:2.2.0"
      ],
      "env": {
        "PORT": "3000",
        "HTTP_PROXY": "<your HTTP_PROXY>",
        "BROWSER_USER_DATA_DIR": "~/.cache/mcp-web-research/chrome-profile",
        "BROWSER_TIMEOUT_MS": "30000",
        "MAX_CONCURRENT_PAGES": "5",
        "MAX_REQUESTS_BEFORE_RECYCLE": "1000",
        "MAX_CONTENT_LENGTH": "5242880",
        "NETWORK_IDLE_TIMEOUT_MS": "5000",
        "SCROLL_DELAY_MS": "500",
        "SCROLL_STEP_PX": "1000",
        "SCROLL_SETTLE_TIMEOUT_MS": "500",
        "MAX_SCROLL_STEPS": "6",
        "SEARCH_WAIT_TIMEOUT_MS": "10000",
        "READABILITY_CHAR_THRESHOLD": "20"
      }
    }
  }
}
One line, from the terminal
Claude Code
claude mcp add --env PORT=3000 --env HTTP_PROXY='<your HTTP_PROXY>' --env BROWSER_USER_DATA_DIR='~/.cache/mcp-web-research/chrome-profile' --env BROWSER_TIMEOUT_MS=30000 --env MAX_CONCURRENT_PAGES=5 --env MAX_REQUESTS_BEFORE_RECYCLE=1000 --env MAX_CONTENT_LENGTH=5242880 --env NETWORK_IDLE_TIMEOUT_MS=5000 --env SCROLL_DELAY_MS=500 --env SCROLL_STEP_PX=1000 --env SCROLL_SETTLE_TIMEOUT_MS=500 --env MAX_SCROLL_STEPS=6 --env SEARCH_WAIT_TIMEOUT_MS=10000 --env READABILITY_CHAR_THRESHOLD=20 --transport stdio web-research-mcp -- docker run -i --rm ghcr.io/shukoilab/web-research-mcp:2.2.0
OpenAI Codex CLI
codex mcp add web-research-mcp --env PORT=3000 --env HTTP_PROXY='<your HTTP_PROXY>' --env BROWSER_USER_DATA_DIR='~/.cache/mcp-web-research/chrome-profile' --env BROWSER_TIMEOUT_MS=30000 --env MAX_CONCURRENT_PAGES=5 --env MAX_REQUESTS_BEFORE_RECYCLE=1000 --env MAX_CONTENT_LENGTH=5242880 --env NETWORK_IDLE_TIMEOUT_MS=5000 --env SCROLL_DELAY_MS=500 --env SCROLL_STEP_PX=1000 --env SCROLL_SETTLE_TIMEOUT_MS=500 --env MAX_SCROLL_STEPS=6 --env SEARCH_WAIT_TIMEOUT_MS=10000 --env READABILITY_CHAR_THRESHOLD=20 -- docker run -i --rm ghcr.io/shukoilab/web-research-mcp:2.2.0
VS Code
code --add-mcp '{"name":"web-research-mcp","type":"stdio","command":"docker","args":["run","-i","--rm","ghcr.io/shukoilab/web-research-mcp:2.2.0"],"env":{"PORT":"3000","HTTP_PROXY":"<your HTTP_PROXY>","BROWSER_USER_DATA_DIR":"~/.cache/mcp-web-research/chrome-profile","BROWSER_TIMEOUT_MS":"30000","MAX_CONCURRENT_PAGES":"5","MAX_REQUESTS_BEFORE_RECYCLE":"1000","MAX_CONTENT_LENGTH":"5242880","NETWORK_IDLE_TIMEOUT_MS":"5000","SCROLL_DELAY_MS":"500","SCROLL_STEP_PX":"1000","SCROLL_SETTLE_TIMEOUT_MS":"500","MAX_SCROLL_STEPS":"6","SEARCH_WAIT_TIMEOUT_MS":"10000","READABILITY_CHAR_THRESHOLD":"20"}}'

Syntax from each client's docs (Claude Code: claude mcp add; Codex: codex mcp add; VS Code: code --add-mcp). Placeholders in angle brackets are values you fill in.

Environment variables
  • PORTHTTP port for streamable MCP and health check endpoints (default: 3000)
  • HTTP_PROXYsecretOptional HTTP/HTTPS proxy URI (e.g. http://user:pass@host:port)
  • BROWSER_USER_DATA_DIRPersistent directory storing Chrome profile, cookies, and cache
  • BROWSER_TIMEOUT_MSDefault navigation timeout in milliseconds
  • MAX_CONCURRENT_PAGESMaximum simultaneous browser tabs allowed by semaphore
  • MAX_REQUESTS_BEFORE_RECYCLELifetime requests before background browser restart to prevent RAM fragmentation
  • MAX_CONTENT_LENGTHUpper bound memory guard in bytes against massive HTML payloads
  • NETWORK_IDLE_TIMEOUT_MSMaximum wait time in ms for initial network stabilization before scrolling
  • SCROLL_DELAY_MSDebounce delay in ms after each scroll and semantic unfolding step
  • SCROLL_STEP_PXDistance in pixels per scroll increment
  • SCROLL_SETTLE_TIMEOUT_MSFinal quiet period in ms after scroll loop completes
  • MAX_SCROLL_STEPSMaximum scroll iterations for lazy content hydration and DOM convergence
  • SEARCH_WAIT_TIMEOUT_MSMaximum wait time in ms for Google SERP cards to render before parsing results
  • READABILITY_CHAR_THRESHOLDMinimum character length for Mozilla Readability article scoring

A starting point — check the repository for exact arguments and setup. Restart your client after editing the config.

Category
Search & Web
Version
2.2.0
Registry
active
Published
11/22/2026
Listed in:Official MCP registry ↗how this is checked

Is it safe? Is it maintained?

Serverdex check: Nov 22, 2026

Looks healthy: Web Research MCP Server is maintained, open source.

Maintained
Active
Last commit 2 days ago (Nov 20, 2026), 0 open issues.
Official registry
Active
Published as io.github.shukoilab/web-research-mcp in the official MCP registry, version 2.2.0.
Source
Open source, MIT
Public repository under the MIT licence, 0 stars, 0 forks.
Runs
On your machine
A local Docker package started by your client; it can reach whatever your user account can.
Credentials
1 required
Declared environment variables: HTTP_PROXY. They stay on your machine; the config on this page shows where each goes.
Owner
Unclaimed
Nobody has claimed this page yet; the data above comes from the registry, GitHub and the live check.

Facts only: last commit and licence from GitHub, the entry's status from the official registry, credentials from the live check. Not a code audit — run the security scan on the endpoint yourself.

On GitHub

read Nov 21, 2026
Stars
0
Forks
0
Last push
Nov 20, 2026
License
MIT

TypeScriptgooglemarkdownmcpsearch-engineweb

From the README

🎭 MCP Web Research Server Enterprise-Grade, Ultra-Fast, and Production-Ready Web Research Model Context Protocol (MCP) Server. Engineered for AI coding agents and autonomous workflows requiring high-accuracy Google Search and high-density, token-efficient webpage content extraction with undetectable anti-bot evasion. 🌟 Key Architectural Features • 🎭 100% Undetectable Headed Stealth on Display :99: Built on Patchright (patched driver eliminating Runtime.enable, --enable-automation, and console leaks). Enforces official Google Chrome in genuine headed mode (headless: false) inside an isolated X11 virtual framebuffer (:99) adhering strictly to Patchright's official Zero-Injection Best Practice (zero custom args, zero custom user-agent, zero header tampering). Guarantees 100% authentic consumer browser window metrics and extensions state with zero desktop window pop-ups or focus-stealing on the host OS. • ⚡ Pre-Warmed Persistent Pool ( disclosures with zero language-locking, unclamps CSS line-clamping, and stops when DOM height converges. • 📉 Token-Efficient & High-Density Markdown: Strips token-wasting avatar images, promotional widgets, and redundant blank lines.…

Read the full README on GitHub →

The most-starred Search & Web servers in the index, with their live-check result.

ServerStarsLast pushLive check
Browser Use121,623Nov 2026Working
Scrapling MCP Server104,822Nov 2026Local / not checked
Chrome DevTools MCP58,028Nov 2026Local / not checked
Chrome DevTools MCP58,014Nov 2026Local / not checked
com.puter MCP Server44,182Nov 2026Needs sign-in

Web Research MCP Server: questions people ask

Is Web Research MCP Server a remote or a local MCP server?
According to its entry in the official MCP registry, Web Research MCP Server ships as a local package (Docker) that your client starts on your machine.
Does Web Research MCP Server need an API key?
Its registry entry declares one required environment variable: HTTP_PROXY. The config on this page shows where each goes.
Is Web Research MCP Server safe to use?
Looks healthy: Web Research MCP Server is maintained, open source. In detail — maintained: Active; official registry: Active; source: Open source, MIT; runs: On your machine; credentials: 1 required. Serverdex check of Nov 22, 2026. This is a reading of the repository, the registry entry and the live check, not a code audit; run the Serverdex security scan on the endpoint before trusting it with real data.
Is Web Research MCP Server still maintained?
Active: the repository's last commit 2 days ago. Last push Nov 20, 2026, 0 GitHub stars, MIT licence. Read from GitHub on Nov 21, 2026.
How do I add Web Research MCP Server to Claude, Cursor or VS Code?
Copy the config in "Connect this server" into your client's MCP config file (claude_desktop_config.json, ~/.cursor/mcp.json or .vscode/mcp.json), or use the one-click Add to Cursor / Add to VS Code buttons and the one-line commands for Claude Code and Codex; then restart the client.
Browse all Search & Web →

Add the badge to your site

Show visitors that Web Research MCP Server is listed here — it’s also the link we check for a free listing.

Web Research MCP Server — listed on Serverdex

HTML — for your website

<a href="https://serverdex.io/server/io-github-shukoilab-web-research-mcp?utm_source=badge"><img src="https://serverdex.io/brand/badge.svg" alt="Web Research MCP Server — listed on Serverdex" width="123" height="40" loading="lazy"></a>

Recommended. A dofollow link from your own domain is the one that counts for search engines, and it's the link we check for a free listing.

Markdown — for your README

[![Web Research MCP Server — listed on Serverdex](https://serverdex.io/brand/badge.svg)](https://serverdex.io/server/io-github-shukoilab-web-research-mcp?utm_source=badge)

Nice for visibility, but GitHub marks README links nofollow, so it doesn't pass authority. Use the HTML badge on your site as well.

Add to CursorAdd to VS CodeOpen in Claude Code

Install buttons — for your README

[![Add to Cursor](https://serverdex.io/brand/install-cursor.svg)](https://serverdex.io/install/cursor/io-github-shukoilab-web-research-mcp) [![Add to VS Code](https://serverdex.io/brand/install-vscode.svg)](https://serverdex.io/install/vscode/io-github-shukoilab-web-research-mcp) [![Open in Claude Code](https://serverdex.io/brand/install-claude-code.svg)](https://serverdex.io/install/claude-code/io-github-shukoilab-web-research-mcp)

One click opens Cursor or VS Code with this server's config prefilled; the Claude Code button lands on the one-line command. The links point at Serverdex, so when your config changes the buttons keep working.

Install buttons — HTML for your docs

<a href="https://serverdex.io/install/cursor/io-github-shukoilab-web-research-mcp"><img src="https://serverdex.io/brand/install-cursor.svg" alt="Add to Cursor — via Serverdex" width="140" height="28"></a>
<a href="https://serverdex.io/install/vscode/io-github-shukoilab-web-research-mcp"><img src="https://serverdex.io/brand/install-vscode.svg" alt="Add to VS Code — via Serverdex" width="147" height="28"></a>
<a href="https://serverdex.io/install/claude-code/io-github-shukoilab-web-research-mcp"><img src="https://serverdex.io/brand/install-claude-code.svg" alt="Open in Claude Code — via Serverdex" width="180" height="28"></a>

Same buttons as plain links for a docs page or website.

Prefer a live badge with the score, stars and live check? Score badge (links to a page that explains the number and back to this listing).