InnerVault

Library

85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.

Results

Looks like a goal we have a starting path for: I want to research potential clients

  1. pi-research

    Skills

    Web research for your agents with smart and safe tooling + knowledge store

    Stale GitHub, Lincoln504 66 ★MITUpdated 4 days ago

    git clone https://github.com/Lincoln504/pi-research.git
  2. trafilatura

    AI repositories

    Python & Command-line tool to gather text and metadata on the Web: Crawling, scraping, extraction, output as CSV, JSON, HTML, MD, TXT, XML

    Indexed GitHub, adbar 7,128 ★Apache-2.0Updated 3 days ago

    git clone https://github.com/adbar/trafilatura.git
  3. google-search

    MCP servers

    A Playwright-based Node.js tool that bypasses search engine anti-scraping mechanisms to execute Google searches. Local alternative to SERP APIs with MCP server integration.

    Stale GitHub, web-agent-master 623 ★Updated 19 months ago

    git clone https://github.com/web-agent-master/google-search.git
  4. CRW Web Scraper

    MCP servers

    Open-source web scraper for AI agents with scrape, crawl, and map tools

    Stale Official MCP Registry, io.github.us Updated 58 days ago 1 note

    ghcr.io/us/crw:latest
  5. oc

    Agents & frameworks

    Turn any website into a compact CLI tailored for AI agents. Browse the web in hundreds of tokens, not tens of thousands.

    Stale GitHub, only-cli 636 ★MITUpdated 6 days ago

    git clone https://github.com/only-cli/oc.git
  6. xpay Web Scraping

    MCP servers

    35+ web scraping tools. Firecrawl, Bright Data, Jina, Olostep, ScrapeGraph, Notte, Riveter.

    Stale Official MCP Registry, io.github.xpaysh Updated 8 months ago 1 note

  7. firecrawl-mcp-server

    MCP servers

    Official Firecrawl MCP server, the context API for AI agents: search, scrape, and interact with the web, plus parse, crawl, map, Agent and Monitor, from any MCP client.

    Indexed GitHub, firecrawl 7,836 ★MITUpdated today

    git clone https://github.com/firecrawl/firecrawl-mcp-server.git
  8. WebAI2API

    AI repositories

    WebAI2API: 基于 Camoufox 的网页 AI 转 API 工具,支持 LMArena/Gemini等,多窗口并发与账号隔离。 | Web AI to OpenAI API via Camoufox. Supports LMArena/Gemini and more, multi-window concurrency & account isolation.

    Stale GitHub, foxhui 1,388 ★MITUpdated 4 months ago

    git clone https://github.com/foxhui/WebAI2API.git
  9. camoufox-cli

    Agents & frameworks

    Anti-detect browser automation CLI & Skills for AI agents — Camoufox-powered fingerprint spoofing, no bot-detectable Playwright leaks

    Stale GitHub, Bin-Huang 361 ★MITUpdated 6 days ago

    git clone https://github.com/Bin-Huang/camoufox-cli.git
  10. wigolo

    AI repositories

    The go-to web for your AI coding agent — local-first search, fetch, crawl & research over MCP. No API keys, no cloud, $0/query. Public beta.

    Indexed GitHub, KnockOutEZ 5,546 ★Custom licence (see repository)Updated yesterday

    git clone https://github.com/KnockOutEZ/wigolo.git
  11. cli

    Skills

    Firecrawl CLI and agent skills: search, scrape, and interact with the web from your terminal or any coding agent, plus parse, crawl, map, Agent and Monitor. Firecrawl is the context API for AI agents.

    Stale GitHub, firecrawl 678 ★Updated 10 days ago

    git clone https://github.com/firecrawl/cli.git
  12. agent-skills

    Skills

    Agent skills that teach AI coding agents to use Decodo for web scraping

    Stale GitHub, Decodo 7 ★MITUpdated 13 days ago

    git clone https://github.com/Decodo/agent-skills.git
  13. Website crawling, Google search and Wikipedia lookup as agent tools.

    Stale Official MCP Registry, com.thenextgennexus Updated 9 days ago 1 note

  14. apitap

    MCP servers

    CLI, MCP server, and npm library that turns any website into an API — no docs, no SDK, no browser.

    Stale GitHub, n1byn1kt 130 ★Apache-2.0Updated 26 days ago

    git clone https://github.com/n1byn1kt/apitap.git
  15. servo-fetch

    Skills

    A self-contained browser engine that fetches, renders, and extracts web content as Markdown, JSON, or screenshots — no Chromium, no API key, no setup.

    Stale GitHub, konippi 163 ★Apache-2.0Updated 12 days ago

    git clone https://github.com/konippi/servo-fetch.git
  16. x402-gated web scraping MCP server. Pay 0.01 USDC per page on Base. Returns clean Markdown via JSDOM

    Stale Official MCP Registry, io.github.Timwal78 Updated 3 months ago 2 notes

  17. MinerU-HTML

    AI repositories

    MinerU-HTML: An SLM-powered HTML main content extractor that outputs clean HTML bodies. Perfect for Deep Research Agents, RAG applications, and training data generation.

    Stale GitHub, opendatalab 299 ★Apache-2.0Updated 10 days ago

    git clone https://github.com/opendatalab/MinerU-HTML.git
  18. Ultimate Web Scraper

    MCP servers

    Scrape and crawl websites into queryable tables: products, leads, Shopify catalogs, real estate.

    Stale Official MCP Registry, com.ultimatewebscraper Updated 2 months ago 1 note

  19. agentql-mcp

    MCP servers

    Model Context Protocol server that integrates AgentQL's data extraction capabilities.

    Indexed GitHub, tinyfish-io 183 ★MITUpdated 2 days ago

    git clone https://github.com/tinyfish-io/agentql-mcp.git
  20. GoAI Moat Web Scrape

    MCP servers

    Scrape any URL into clean LLM-ready Markdown, or crawl a whole site.

    Stale Official MCP Registry, com.goaimoat Updated 53 days ago 1 note

  21. web-scraping

    MCP servers

    superagnt: marketing plugin for Claude and ChatGPT. Know your market: scrape and search the web.

    Stale Official MCP Registry, com.superagnt Updated 18 days ago 1 note

  22. Extract clean markdown from any URL. Removes boilerplate. For RAG pipelines. x402.

    Stale Official MCP Registry, io.github.Br0ski777 Updated 6 months ago 1 note

  23. HasData Web Scraping

    MCP servers

    Fetch any public web page through managed proxies, with optional JS rendering and extraction rules.

    Stale Official MCP Registry, com.hasdata Updated 53 days ago 3 notes

    @hasdata/web-scraping-mcp@1.0.2
  24. web-scraper

    MCP servers

    Fetch, crawl, and browse protected pages with anti-bot handling - renders in a real browser and

    Stale Official MCP Registry, io.github.DataLeadsPRO Updated 2 months ago 1 note

Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.