Web

rog0x/mcp-web-tools

Gives Claude five web operations without requiring API keys: extract structured content (titles, headings, links, images, metadata) from URLs, search via DuckDuckGo, monitor site uptime and response times, convert HTML to markdown, and batch extract from multiple URLs in parallel. Reaches for this when you need web scraping or search capabilities in your agent workflows but don't want to manage authentication or run a headless browser. Built on direct HTTP requests with 15 second timeouts and strips out scripts and ads for clean extraction. Works through npx so there's no global installation step.

tools: 6
transport: STDIO
last updated: Mar 22, 2026

View on GitHub

Tools

6 tools

Public tool metadata for what this MCP can expose to an agent.

check_usageCheck your current credit balance and API usage history. Free, does not cost a credit. Use this if you need to check how many credits remain or review usage patterns. Returns JSON: {"key": "ftch_abc1...", "credits_remaining": 450, "usage": {"2025-01-15": {"/md": 30, "/s/web":...1 params

Check your current credit balance and API usage history. Free, does not cost a credit. Use this if you need to check how many credits remain or review usage patterns. Returns JSON: {"key": "ftch_abc1...", "credits_remaining": 450, "usage": {"2025-01-15": {"/md": 30, "/s/web":...

Parameters* required

daysinteger

Number of days of usage history to return (default: 30, max: 90)

fetchFetch any webpage and return its content as clean Markdown. This is the default tool for reading web pages. Use this whenever you need to read, summarize, extract information from, or analyze the content of a URL. The response is clean Markdown optimized for LLM context window...2 params

Fetch any webpage and return its content as clean Markdown. This is the default tool for reading web pages. Use this whenever you need to read, summarize, extract information from, or analyze the content of a URL. The response is clean Markdown optimized for LLM context window...

Parameters* required

block_patternsstring

Comma-separated custom strings to detect soft blocks. If any pattern appears in the response body, the request is retried through a different route. Example: premium required,subscribe to read

urlstring

Full URL including scheme (e.g. https://example.com/page)

fetch_htmlFetch a URL and return raw unprocessed HTML. Only use this if you specifically need the HTML source, such as inspecting page structure, meta tags, or debugging rendering issues. In almost all cases, use the "fetch" tool instead, which returns clean Markdown. Returns the full H...2 params

Fetch a URL and return raw unprocessed HTML. Only use this if you specifically need the HTML source, such as inspecting page structure, meta tags, or debugging rendering issues. In almost all cases, use the "fetch" tool instead, which returns clean Markdown. Returns the full H...

Parameters* required

block_patternsstring

Comma-separated custom strings to detect soft blocks. If any pattern appears in the response body, the request is retried through a different route. Example: premium required,subscribe to read

urlstring

Full URL including scheme (e.g. https://example.com/page)

fetch_structured_dataExtract structured data (JSON-LD) from a webpage. Use this when you need machine-readable schema.org data such as product details, recipes, events, articles, reviews, or organization info. Returns a JSON array of structured data objects found on the page. Returns an error if n...2 params

Extract structured data (JSON-LD) from a webpage. Use this when you need machine-readable schema.org data such as product details, recipes, events, articles, reviews, or organization info. Returns a JSON array of structured data objects found on the page. Returns an error if n...

Parameters* required

block_patternsstring

Comma-separated custom strings to detect soft blocks. If any pattern appears in the response body, the request is retried through a different route. Example: premium required,subscribe to read

urlstring

Full URL including scheme (e.g. https://example.com/page)

search_newsSearch for recent news articles. Use this whenever you need current events, breaking news, or recent coverage of a topic. Returns articles with direct URLs to the original sources. Returns JSON: {"query": "...", "params": {"country": "US", "lang": "en"}, "count": 5, "articles"...5 params

Search for recent news articles. Use this whenever you need current events, breaking news, or recent coverage of a topic. Returns articles with direct URLs to the original sources. Returns JSON: {"query": "...", "params": {"country": "US", "lang": "en"}, "count": 5, "articles"...

Parameters* required

countrystring

ISO 3166-1 alpha-2 country code (default: US)

langstring

ISO 639-1 language code (auto-selected from country)

limitinteger

Max results (default: 100)

qstring

Search query

whenstring

Lookback window: 1d 7d 30d 180d

search_webSearch the web and return structured results. Use this whenever you need to find information, look something up, answer factual questions, or find URLs related to a topic. Returns JSON: {"query": "...", "params": {"country": "US", "lang": "en"}, "count": 10, "results": [{"titl...4 params

Search the web and return structured results. Use this whenever you need to find information, look something up, answer factual questions, or find URLs related to a topic. Returns JSON: {"query": "...", "params": {"country": "US", "lang": "en"}, "count": 10, "results": [{"titl...

Parameters* required

countrystring

ISO 3166-1 alpha-2 country code (default: US)

langstring

ISO 639-1 language code (auto-selected from country)

qstring

Search query

whenstring

Time filter: d (past day) w (past week) m (past month) y (past year)

Readme

MCP Web Tools

A powerful MCP (Model Context Protocol) server that gives AI agents web superpowers. Extract content, search the web, monitor sites, and convert HTML to markdown — all through a clean tool interface.

Tools

Tool	Description
`web_extract`	Extract structured content from any URL (title, headings, paragraphs, links, images, metadata)
`web_search`	Search the web via DuckDuckGo — no API key needed
`web_monitor`	Check if a site is up, measure response time, get HTTP headers
`html_to_markdown`	Convert any URL or HTML to clean markdown
`web_multi_extract`	Extract content from multiple URLs in parallel

Installation

For Claude Code

Add to your Claude Code MCP settings (~/.claude/settings.json):

{
  "mcpServers": {
    "web-tools": {
      "command": "npx",
      "args": ["@rog0x/mcp-web-tools"]
    }
  }
}

For Claude Desktop

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "web-tools": {
      "command": "npx",
      "args": ["@rog0x/mcp-web-tools"]
    }
  }
}

Manual Installation

npm install -g @rog0x/mcp-web-tools
mcp-web-tools

View the full README on GitHub

Details

Repository: github.com/rog0x/mcp-web-tools
Categories: Documents & Knowledge, Search & Web Crawling
Package: @rog0x/mcp-web-tools
Transport: STDIO
Registry: MCP registry, active

Web

Tools

Readme

MCP Web Tools

Tools

Installation

For Claude Code

For Claude Desktop

Manual Installation

Details

More from rog0x

Related Documents & Knowledge MCP servers