mcpbeat Sign in

Deepcrawl MCP Server

local only

Deepcrawl runs on your own machine — the client starts it, so there is no endpoint to ping. Last commit 28 Oct 2026.

Clone websites, scrape pages to markdown and crawl whole sites. A free Firecrawl alternative.

—
Installs / week
not published
0
Stars
0 open issues
28 Oct 2026
Last commit
from GitHub
MIT
License
TypeScript

Nothing serious here today

Today is the operative word: we check Deepcrawl every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.

Three servers free · no card

Alternatives to Deepcrawl

same job, measured the same way
Website to Markdown
by saulius876-lgtm

Web pages and whole sites to clean Markdown for RAG and AI agents. Crawls links and sitemaps.

answering
Crawlberg
by xberg-io

Scrape, crawl, and map websites to Markdown or JSON via local CLI.

local only
Kreuzcrawl
by kreuzberg-dev

Scrape, crawl, and map websites to Markdown or JSON via local CLI.

local only
MeshArc
by mesharc

Crawl and scrape websites to clean markdown, and track what changed between crawls.

answering
WebReaper
by alex-on-ai

AI-native web scraper: scrape, crawl and map any site to clean markdown over stdio. MIT-licensed.

local only
PageWire
by pagewire

Web pages to Markdown, metadata and small crawls for agents. Free daily calls, then USDC x402/MPP.

3 tools answering
Tooltrace
by tooltrace

Web tools for AI agents: scrape pages to Markdown, audit SEO, detect tech stacks, check sitemaps

43 installs/wk 7 tools answering
SnoopScan
by snoopscan

Web scraping for agents: scrape, crawl, map, search and extract pages as clean markdown or JSON.

34 tools answering

Deepcrawl — questions

Answers built from our own checks of this server.

Why is there no uptime for Deepcrawl?
Deepcrawl runs on your own machine over stdio — there is no network address to reach, so uptime cannot be measured for it by anyone.
Is Deepcrawl open source?
Yes — it is published under the MIT licence, written in TypeScript and 0 stars on GitHub. The source link is on this page, so you can read exactly what it does with your data before you connect it.