Search & Data Extraction

fetch

modelcontextprotocol

91.5k

Web content fetching and processing for AI consumption.

wigolo

KnockOutEZ

5.5k

Local web search, fetching, crawling, extraction and research, with multi-engine search, local ML reranking, a SQLite cache and JavaScript rendering.

Exa

exa-labs

5.2k

Real-time web search using the Exa AI Search API.

arxiv

blazickjp

3.2k

Search arXiv papers, read original LaTeX sections, get BibTeX from arXiv metadata and set topic watches, with papers stored locally.

trieve

devflowinc

2.7k

Crawl, embed, chunk, search and retrieve information from datasets through Trieve.

brightdata

luminati-io

2.7k

Discover, extract and interact with the web via Bright Data, one interface for automated access to the public internet.

open-webSearch

Aas-ee

1.9k

Multi-engine web search across Bing, Baidu, DuckDuckGo, Brave, Exa and CSDN.

duckduckgo

nickclyde

1.5k

Web search using DuckDuckGo, with content fetching and parsing.

brave-search

brave

1.5k

Web search using Brave's Search API.

SearXNG

ihor-sokoliuk

1.3k

Web search via SearXNG.

crw

us

1.2k

Self-hostable web crawler and search API (fastCRW): scraping, crawling, site mapping and SearXNG-backed search.

fetcher

jae-jae

1.1k

Fetch web page content using a Playwright headless browser, supporting JavaScript rendering, content extraction and Markdown or HTML output.

kagimcp

kagisearch

546

Search the web with Kagi Search.

g-search

jae-jae

273

Google search with parallel queries for multiple keywords.

unsplash

hellokaton

237

Unsplash image search.

TinySearch

MarcellM01

234

Self-hosted web research: SearXNG search with DuckDuckGo fallback, crawling, dense and BM25 reranking and deduplication into a cited, source-grounded prompt.

MinerU-Ecosystem

opendatalab

227

Convert PDFs, Word and PowerPoint files, images and spreadsheets to Markdown via the MinerU document parsing API.

server-deep-research

reading-plus-ai

214

Autonomous deep research with structured query elaboration and concise reporting.

opennutrition

deadletterq

208

Local search of foods, nutrition facts and barcodes in the OpenNutrition database.

simple-arxiv

andybrandt

201

Search and read papers from arXiv.

agentql

tinyfish-io

181

Data extraction with AgentQL.

serpapi

serpapi

180

Search results from Google, Bing, Yahoo, DuckDuckGo, YouTube, eBay and more via SerpApi, plus real-time weather and stock market data.

searxNcrawl

DasDigitaleMomentum

179

Web search via your own SearXNG instance and/or You.com, plus page and site crawling to deduplicated Markdown with Crawl4AI and Playwright, including pages behind a login.

content-core

lfnovo

179

Extract content from web pages, PDFs, Word documents, YouTube transcripts, audio and video with automatic engine selection and structured JSON output.

search1api

fatwang2

173

Web search via Search1API.

simple-pubmed

andybrandt

171

Search and read medical and life sciences papers from PubMed.

scrapeless

scrapeless-ai

169

Web search via the Scrapeless Google SERP API.

read-website-fast

just-every

163

Convert websites to clean Markdown with links preserved, using Mozilla Readability, caching, robots.txt-aware crawling and concurrent fetching.

servo-fetch

konippi

161

Chromium-free web content extraction in a single binary: fetch, render, crawl and screenshot pages with the Servo browser engine.

arxiv-latex

takashiishida

148

Get the LaTeX source of arXiv papers to handle mathematical content and equations.

local-rag

nkapila6

134

Primitive RAG-like web search that runs locally, without external APIs.

searxng

SecretiveShell

131

Connect to SearXNG instances.

brave-search

mikechao

130

Web, image, news, video and local point-of-interest search using Brave's Search API.

google-news

ChanMeng666

129

Google News via SerpAPI: search headlines, stories and related topics, with automatic topic categorization and multi-language support.

vectorize

vectorize-io

115

Retrieval, private deep research, file-to-Markdown extraction and text chunking via Vectorize.

agent-search

lennney

112

Search across DuckDuckGo, Sogou, Bing, Baidu, Wikipedia, Startpage, Yandex and Mojeek with waterfall search, multi-source verification and news search.

screenshot-website-fast

just-every

110

Capture website screenshots, tiling full pages into 1072x1072 chunks for Claude Vision, with configurable viewports and wait strategies for dynamic content.

doc-scraper

Sriram-PR

107

Crawl documentation sites into local Markdown or JSONL corpora and serve them with offline BM25 search, page reads, freshness checks and crawl diffs.

openai-websearch

ConechoAI

94

Expose OpenAI's built-in web search tool.

octagon-deep-research

OctagonAI

94

Deep research agent from Octagon.

naver-search

isnow890

87

Naver Search API integration: blog, news and shopping search plus DataLab analytics.

duckduckgo

zhsama

87

Web search via DuckDuckGo.

wolframalpha

ricocf

86

Access computational knowledge and data via the Wolfram Alpha API.

pdfmux

NameetP

84

PDF extraction router that classifies each page and routes it to PyMuPDF, Docling, OCR or an LLM fallback, re-extracting pages with low confidence scores.

zoomeye

zoomeye-ai

82

Query network asset information from ZoomEye.

bing-search

leehanchung

81

Web search using the Microsoft Bing Search API.

hn

erithwik

76

Search Hacker News, get top stories and more.

reflex

reflex-search

76

Local, offline full-text code search for coding agents using a trigram index over large codebases.