AI-First Scraper
Drops three web scraping tools into Claude Desktop, Cursor, or Cline: fetch_page for single URLs, fetch_pages_batch for up to 25 in parallel, and search_web that runs queries and returns results already converted to Markdown. Strips ads and clutter so your agent gets clean text instead of raw HTML soup. Runs via uvx with zero install, calls the public ai-first-scraper and ai-first-search APIs by default, or point it at your own backend with environment variables. Useful when you need Claude to pull live web content or search results without choking on markup.
- GitHub stars
- 2
- tools
- 3
- transport
- STDIO
- env vars
- 3
- last updated
- Aug 26, 2026
Tools
3 toolsPublic tool metadata for what this MCP can expose to an agent.
fetch_pageFetch one URL → return clean Markdown (HTML or PDF).
Fetch one URL → return clean Markdown (HTML or PDF).
No parameter schema in public metadata yet.
fetch_pages_batchFetch up to 25 URLs in parallel → return Markdown for each.
Fetch up to 25 URLs in parallel → return Markdown for each.
No parameter schema in public metadata yet.
search_webRun a web search and return the top-k result pages already converted to Markdown.
Run a web search and return the top-k result pages already converted to Markdown.
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
SCRAPER_URLURL of the ai-first-scraper instance to use. Default: https://ai-first-scraper.onrender.com
SEARCH_URLURL of the ai-first-search instance to use. Default: https://ai-first-search.onrender.com
AFS_TIMEOUTUpstream HTTP timeout in seconds. Default: 45
Readme
ai-first-scraper-mcp
Plug Claude Desktop, Cursor, or Cline straight into an ad-free web scraper + search engine. Three tools, one line of config.
What it does
Adds three tools to any MCP-compatible agent:
| Tool | What it does |
|---|---|
fetch_page | Fetch one URL → return clean Markdown (HTML or PDF). |
fetch_pages_batch | Fetch up to 25 URLs in parallel → return Markdown for each. |
search_web | Run a web search and return the top-k result pages already converted to Markdown. |
No more "the model called curl and then tried to parse 80kB of ad HTML." Your agent receives clean Markdown ready to reason about.
Details
- Repository
- github.com/yubinkim444/ai-first-scraper-mcp
- Categories
- Documents & Knowledge, Search & Web Crawling
- Package
ai-first-scraper-mcp- Transport
- STDIO
- Registry
- MCP registry, active
More from yubinkim444
Related Documents & Knowledge MCP servers
View all
Agent Moduleagentmodule/mcpDeterministic compliance and vertical knowledge bases for autonomous agents. Free 24hr trial.0stars
Searxng Deepdiveburakaydinofficial/searxng-deepdiveMCP server for SearXNG with engine targeting, multi-page fanout, and HTML→Markdown URL reading.1stars
Fodda Knowledge Graphspiers-fawkes/fodda-mcpExpert-curated knowledge, brand, research & earnings intelligence — 56 tools, 220+ graphs.1stars
Danbooru Tagsgamzadongza/danbooru-tags-mcpExtract tags from any Danbooru post and explore categories at a glance. Analyze character-specific tag frequencies to surface top traits and clothing patterns. 1stars
Brewers Almanackgregario/brewers-almanackBrewing knowledge MCP — beer styles, ingredients, off-flavours, water chemistry, recipes1stars
Groupdocs Metadata Mcpgroupdocs-metadata/groupdocs.metadata.mcpMCP server for GroupDocs.Metadata — read, search, write, and remove document metadata.1stars