Claude MarketplacesSubmit
bamchi avatar

Scrapi

bamchi/scrapi-mcp-server

If you've ever needed Claude to actually read a webpage instead of hallucinating about it, this is the fix. Scrapi exposes two tools: fetch a URL as clean Markdown (preserving structure) or plain text, with metadata like title and publish date. It handles JavaScript rendering, strips ads and navigation cruft, and bypasses basic anti-bot measures. Runs over stdio via npx or streamable HTTP if you don't want Node.js on the client. Free tier gives you 500 credits monthly. Built by a team running 1,900+ production scrapers, so the anti-bot logic is battle tested, not wishful thinking.

GitHub stars
5
tools
5
auth
Secret needed
transport
STDIO, HTTP
env var
1
last updated
Feb 12, 2026
View on GitHub

Install

From registry metadata
$ npx add-mcp https://scrapi.ai/mcp --name scrapi --header 'Authorization: Bearer ${API_TOKEN}'

Run in your terminal. add-mcp asks which agents to add it to, then asks for each value it needs. Add -g to install it for every project.

Review the command, arguments and environment values before installing. MCP servers run with your local permissions.

Other ways

Claude Code

$ claude mcp add --transport http scrapi https://scrapi.ai/mcp --header 'Authorization: YOUR_AUTHORIZATION'

Run in your terminal. Add --scope user to make it available in every project.

Tools

Verified live · 5 tools

Verified live against the running server on Nov 6, 2026.

scrape_urlScrapes a webpage and returns the content in AI-readable Markdown format. Can access blocked sites through browser rendering.2 params

Scrapes a webpage and returns the content in AI-readable Markdown format. Can access blocked sites through browser rendering.

Parameters* required
formatstring
Output format: markdown (default) or textone of markdown · textdefault: markdown
url*string
The URL of the webpage to scrape
scrape_urlsScrapes multiple webpages in parallel and returns the content in AI-readable Markdown format. Can access blocked sites through browser rendering.2 params

Scrapes multiple webpages in parallel and returns the content in AI-readable Markdown format. Can access blocked sites through browser rendering.

Parameters* required
formatstring
Output format: markdown (default) or textone of markdown · textdefault: markdown
urls*array
URLs to scrape (max 10)
get_usageCheck API usage and remaining credits. Returns current plan, subscription credits, purchased credits, and total remaining credits.

Check API usage and remaining credits. Returns current plan, subscription credits, purchased credits, and total remaining credits.

No parameters. Call it with no arguments.

scraper_server_statusCheck the status of all ScraperServer instances. Shows server health, circuit breaker state, failure counts, and last success/failure times.

Check the status of all ScraperServer instances. Shows server health, circuit breaker state, failure counts, and last success/failure times.

No parameters. Call it with no arguments.

get_billingRetrieve MCP billing information: subscription details, available plans, daily usage history, or spending limits.3 params

Retrieve MCP billing information: subscription details, available plans, daily usage history, or spending limits.

Parameters* required
action*string
What billing info to retrieve: subscription (current plan details), plans (available plans), daily_usage (credit usage history), spending_limits (daily spend limit status)one of subscription · plans · daily_usage · spending_limits
end_datestring
End date for daily_usage (YYYY-MM-DD). Default: today
start_datestring
Start date for daily_usage (YYYY-MM-DD). Default: 30 days ago

Sponsors

Promote your product hereReach 125k+ visitors monthlyPromote your product hereReach 125k+ visitors monthlyAgent CaffeineSponsoredClose your lid, come back to finished workSnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthlyWaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthlyknobsSponsoredSee your site on any phone, any day, in any language

Configuration

SCRAPI_API_KEY*secret

Your Scrapi API key (get one free at https://scrapi.ai/dashboard)

Readme

Scrapi AI

MCP server that converts URLs to clean Markdown/Text for LLM agents

한국어 · Website · Dashboard

npm version License: MIT

⚡ Fast & Reliable — Built on 8+ years of web scraping expertise, 1,900+ production crawlers, and battle-tested anti-bot handling.

What is this?

View the full README on GitHub

Details

Repository
github.com/bamchi/scrapi-mcp-server
Categories
AI & LLM Tools, Documents & Knowledge, Search & Web Crawling
Package
@scrapi.ai/mcp-server
Transport
STDIO, HTTP
Auth
Required
Registry
MCP registry, active
Tools verified
Nov 6, 2026

Related AI & LLM Tools MCP servers

View all
1eidetic-works avatarNucleuseidetic-works/nucleus-mcpPersistent memory for AI agents — shared .brain across Claude Code, Cursor & Codex5stars
2kokogo100 avatarRagalgokokogo100/ragalgo-mcp-serverDynamic RAG Engine preventing AI hallucinations in Korean Finance and Crypto markets.5stars
3lumabyteco avatarClarifypromptlumabyteco/clarifyprompt-mcpAI prompt optimization for 58+ platforms across 7 categories with custom platforms5stars
4mcp-s-ai avatarImage Recognition Mcpmcp-s-ai/image-recognition-mcpMCP server for AI-powered image recognition and description using OpenAI vision models.5stars
5mcp-s-ai avatarImage Recongnition Mcpmcp-s-ai/image-recongnition-mcpMCP server for AI-powered image recognition and description using OpenAI vision models.5stars
6pineapple-farm avatarSkill Historypineapple-farm/skill-historyTrack download history for 70,000+ agent skills. Search and get daily snapshots.5stars