A search for crunchjunkie

Search for:

A search for crunchjunkie

View all MCP Servers

Why this server?
A local crawler that 'crunches' web pages into token-efficient Markdown, the closest fit for a data/content-crunching handle like 'crunchjunkie'.
LookaCrawler
Browser Automation Research & Data Web Scraping
lucasmartins-ai
A
license
A
quality
A
maintenance
Free, open-source, token-efficient local alternative to Firecrawl with a native Model Context Protocol (MCP) server. Achieves >73% token reduction by pruning web noise before Markdown extraction, uses Playwright with stealth fingerprint patches to bypass anti-bot challenges.
Updated 7 days ago (2026-10-14 18:58 UTC)
9
3
MIT
Why this server?
Converts audio, video, images, documents, and webpages into text or Markdown — ideal for someone who likes crunching mixed-format content into usable text.
textify-mcp
textifyme
A
license
Not graded
quality
C
maintenance
A local stdio shim for the hosted Textify MCP server that converts audio, video, images, documents, and webpages into text or Markdown. Includes tools for YouTube transcripts, audio transcription, OCR, file-to-Markdown, and webpage-to-Markdown extraction.
Updated 2 months ago (2026-08-19 19:54 UTC)
4 npm
MIT
Why this server?
Does the heavy crunching of DOCX/XLSX files, extracting native chart data and figures with zero loss, useful for a data-crunching user.
refigure
RAG Systems Data Platforms Documentation Access
HelgDemidov
A
license
Not graded
quality
A
maintenance
Converts DOCX/XLSX to Markdown with native OOXML chart-data extraction (reads numCache/strCache directly, no OCR or rasterization) and zero-loss composite-figure markers. Ships a CLI, an MCP server (stdio + Streamable HTTP), and an optional VLM fallback for figures with no native chart data.
Updated 7 days ago (2026-10-14 19:37 UTC)
87 PyPI
Apache 2.0
Why this server?
Crunching and indexing historical AI chat logs into a searchable memory vault with token stripping — relevant to power-user 'junkie' workflows.
Chronicle MCP
Knowledge & Memory Search RAG Systems
Leviathan0x0
A
license
B
quality
B
maintenance
Chronicle is a secure, local-first MCP server designed to transform your historical AI chat logs into a persistent memory vault. It seamlessly parses and indexes raw conversation exports from ChatGPT, Claude, and various IDE transcripts directly on your machine. By utilizing dynamic token-stripping, the engine automatically cleans redundant syntax wrappers to save up to 40%
Updated 4 days ago (2026-10-17 08:11 UTC)
8
2
MIT
Why this server?
Fast local webpage fetching and crawling that reduces content to clean Markdown, matching a crunching/scraping enthusiast's needs.
read-website-fast
Browser Automation Web Scraping RAG Systems
rangel43544
F
license
Not graded
quality
A
maintenance
Enables AI agents and LLM pipelines to fetch webpages or crawl sites locally and convert the content into clean, token-efficient Markdown with links preserved. Includes caching, robots.txt-aware rate limiting, concurrent depth crawling, and optional chunking for downstream processing.
Updated 5 days ago (2026-10-16 18:03 UTC)
-
Why this server?
Ultra-fast Rust web fetcher that crunches any URL into clean Markdown with anti-fingerprinting and cookie auth.
nab
Web Scraping Browser Automation Search
MikkoParkkola
A
license
A
quality
A
maintenance
Ultra-fast web fetcher and MCP server written in Rust. Fetches any URL as clean Markdown with HTTP/3, JavaScript rendering, anti-fingerprinting, browser cookie authentication from Chrome/Firefox/Brave, and 1Password integration.
Updated 3 days ago (2026-10-18 09:37 UTC)
8
16
MIT
Why this server?
Enterprise-scale website-to-Markdown extraction that cuts token costs by 90%, a strong match for bulk content crunching.
flycrawlofficial
Browser Automation Web Scraping RAG Systems
FlyCrawl-ai
A
license
A
quality
B
maintenance
Turn Any Website Into Clean Fit-Markdown for AI Extract clean, structured Markdown from any static or dynamic website at enterprise scale. Reduce token costs by 90% and feed pure signal into your RAG pipelines and AI agents.
Updated 4 days ago (2026-10-17 13:07 UTC)
4
1
MIT
Why this server?
Crunches large comic archives (CBZ/CBR) into Kindle-optimized EPUBs with chunking — a niche heavy-processing tool fitting the 'junkie' vibe.
kcc-epub-converter
Multimedia Processing Image & Video Processing
AmitKumarMyT
F
license
Not graded
quality
C
maintenance
Converts large comic archives (CBZ/CBR) into Kindle-optimized EPUB volumes with GPU acceleration, smart chunking under Amazon's 200MB limit, and device-specific profiles for manga/comics.
Updated 3 months ago (2026-08-05 11:58 UTC)
-
Why this server?
Deterministically crunches multi-turn conversation history to cut token costs 40-60%, appealing to efficiency-focused power users.
genpark-agentic-promptofficial
AI & Machine Learning Agent Orchestration
alphaparkinc
A
license
Not graded
quality
B
maintenance
Compresses multi-turn conversation history by stripping verbose boilerplate and filler tokens while preserving critical tool parameters and named entities, deterministically cutting inference costs by 40-60%. Runs as a zero-dependency Python MCP server or importable module, compatible with Claude Desktop, Cursor, and other MCP runtimes.
Updated 16 days ago (2026-10-05 23:21 UTC)
7
MIT

flycrawlofficial

genpark-agentic-promptofficial