mirror of
https://github.com/punkpeye/awesome-mcp-servers.git
synced 2026-09-10 17:45:57 +00:00
Merge pull request #10944 from igorsaevets/add-page2ai-mcp
Add page2ai-mcp to Search & Data Extraction 🤖🤖🤖
This commit is contained in:
@@ -3175,6 +3175,7 @@ Tools for conducting research, surveys, interviews, and data collection.
|
||||
- [JerryLiu369/agent-web-search](https://github.com/JerryLiu369/agent-web-search) [](https://glama.ai/mcp/servers/JerryLiu369/agent-web-search) 🐍 ☁️ 🏠 - Agent-native web search for AI agents: one provider-neutral `web_search` tool aggregating model-native grounding (ARK, Gemini, Grok, DeepSeek, Zhipu) and agent search APIs (Exa, Parallel, Brave, Perplexity, Tavily, You.com). Keyless free defaults, stdio + stateless Streamable-HTTP MCP, CLI, Python API, and Hermes plugin. Install via `pipx install agent-web-search-mcp`.
|
||||
- [artemchuikin/youtube-mcp](https://github.com/artemchuikin/youtube-mcp) [](https://glama.ai/mcp/servers/artemchuikin/youtube-mcp) 🎖️ 📇 ☁️ - YouTube transcripts in five formats (text, JSON, SRT, VTT, srv3), video and channel search, playlists, and 4,000-video batch jobs over a hosted endpoint. 14 tools, free tier, no card.
|
||||
- [Newscatcher/catchall-mcp](https://github.com/Newscatcher/catchall-mcp) [](https://glama.ai/mcp/servers/Newscatcher/catchall-mcp) 🐍 ☁️ - Recall-first web search: finds every relevant event across the open web, not just the top results.
|
||||
- [igorsaevets/page2ai-mcp](https://github.com/igorsaevets/page2ai-mcp) [](https://glama.ai/mcp/servers/igorsaevets/page2ai-mcp) 📇 🏠 - Convert any web page URL into clean Markdown for LLM context. Runs entirely on your machine with no external API calls and no API key. Preserves tables, code blocks and heading structure. Install via `npx -y @page2ai/mcp`.
|
||||
- [pgalyen1987/gate402-mcp](https://github.com/pgalyen1987/gate402-mcp) [](https://glama.ai/mcp/servers/pgalyen1987/gate402-mcp) 📇 ☁️ - Pay-per-call agent APIs over x402 (USDC on Base): per-token LLM inference (Llama 3.1/Qwen/Mistral), per-second GPU/CPU compute, on-chain/DeFi + SEC-EDGAR + news data, and clean-Markdown/Cloudflare-stealth web scraping. Signed receipts, no signup — auto-claims a free-tier key. Install via `npx -y gate402-mcp`.
|
||||
- [KnockOutEZ/wigolo](https://github.com/KnockOutEZ/wigolo) [](https://glama.ai/mcp/servers/KnockOutEZ/wigolo) 📇 🏠 - Local-first, keyless web intelligence in one server: search, fetch, crawl, extract, cache, find-similar, and research. Multi-engine search with local ML reranking and a persistent SQLite cache, renders JS-heavy pages, and keeps everything on your machine. Install via `npx wigolo init --non-interactive --agents=<agent>`.
|
||||
- [newsagentdata/newsagent-mcp](https://github.com/newsagentdata/newsagent-mcp) [](https://glama.ai/mcp/servers/newsagentdata/newsagent-mcp) 🐍 ☁️ - Real-time, ML-enriched news intelligence — urgency scoring, political lean & event clustering across 190+ countries.
|
||||
|
||||
Reference in New Issue
Block a user