webclaw
Reach for this when you need to pull web content into a clean, usable format without wrestling with HTML parsing yourself. It handles the full pipeline from fetching arbitrary URLs to extracting the meaningful content and converting it to markdown. You can scrape individual pages, crawl through sites, or get AI-generated summaries of what you extract. The stdio transport makes it straightforward to pipe into Claude or other MCP clients. Saves you from spinning up headless browsers or dealing with the usual web scraping headaches when you just need structured text from the web.
- GitHub stars
- 2.4K
- tools
- 12
- auth
- Secret needed
- transport
- STDIO, HTTP
- env var
- 1
- last updated
- Nov 3, 2026
Tools
12 toolsPublic tool metadata for what this MCP can expose to an agent.
scrapeExtract one URL as markdown, text, JSON, LLM format, or HTML
Extract one URL as markdown, text, JSON, LLM format, or HTML
No parameter schema in public metadata yet.
selectPick values or records from a page with CSS selectors or XPath, its data tables, elements found by text, or every element like an example, as JSON
Pick values or records from a page with CSS selectors or XPath, its data tables, elements found by text, or every element like an example, as JSON
No parameter schema in public metadata yet.
screenshotCapture a page's viewport or the whole page as PNG or JPEG, print it to PDF, or save it as one MHTML file
Capture a page's viewport or the whole page as PNG or JPEG, print it to PDF, or save it as one MHTML file
No parameter schema in public metadata yet.
crawlFollow same-origin links and extract discovered pages, most relevant first with a query
Follow same-origin links and extract discovered pages, most relevant first with a query
No parameter schema in public metadata yet.
mapDiscover URLs from sitemaps, a short crawl and the Common Crawl index without extracting every page
Discover URLs from sitemaps, a short crawl and the Common Crawl index without extracting every page
No parameter schema in public metadata yet.
batchScrape multiple URLs in parallel
Scrape multiple URLs in parallel
No parameter schema in public metadata yet.
extractConvert page content into structured data
Convert page content into structured data
No parameter schema in public metadata yet.
summarizeSummarize a page
Summarize a page
No parameter schema in public metadata yet.
diffCompare page content snapshots
Compare page content snapshots
No parameter schema in public metadata yet.
brandExtract colors, fonts, logos, and metadata
Extract colors, fonts, logos, and metadata
No parameter schema in public metadata yet.
searchSearch the web and scrape results
Search the web and scrape results
No parameter schema in public metadata yet.
researchMulti-source research workflow
Multi-source research workflow
No parameter schema in public metadata yet.
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageConfiguration
WEBCLAW_API_KEYsecretOptional Webclaw API key. Enables cloud fallback for bot-protected and JavaScript-heavy pages.
Readme
English | 简体中文
webclaw
Turn websites into clean markdown, JSON, and LLM-ready context.
CLI, MCP server, REST API, and SDKs for AI agents and RAG pipelines.
Details
- Repository
- github.com/0xmassi/webclaw
- Website
- webclaw.io
- Category
- Search & Web Crawling
- Package
@webclaw/mcp- Transport
- STDIO, HTTP
- Auth
- Required
- Registry
- MCP registry, active
Related Search & Web Crawling MCP servers
View all
Open-WebSearchaas-ee/open-websearchWebSearchMCP using free multi-engine search (NO API KEYS REQUIRED) — Supports Bing, Baidu, DuckDuckGo, Brave, Exa, Github, Juejin and CSDN.1.2Kstars
Octocode MCP - AI Context Platformbgauryy/octocode-mcpAI code research platform. Search, analyze, and extract insights from any GitHub repository.863stars
OrchestKit Docs MCPyonatangross/orchestkitRead-only MCP server for the OrchestKit docs: full-text search + Markdown fetch. No auth.302stars
DeepContextwildcard-official/deepcontext-mcpProvides symbol-aware semantic search for large codebases via MCP with index, search, status, and clear operations.276stars
searxNcrawldasdigitalemomentum/searxncrawlWeb search via SearXNG and/or You.com, plus clean Markdown crawling via Crawl4AI. Self-hosted.185stars
SerpApiserpapi/serpapi-mcpOfficial SerpApi MCP server for Google, Bing, and other search engines.184stars