feat: add jlucasmcrell/apify-scrapers to Search & Data Extraction

This commit is contained in:
joeygambino
2026-09-10 19:31:06 -04:00
parent 5c2e35ed71
commit 0264587681
+1 -1
View File
@@ -3275,6 +3275,7 @@ Tools for conducting research, surveys, interviews, and data collection.
### 🔎 <a name="search"></a>Search & Data Extraction
- [JerryLiu369/agent-web-search](https://github.com/JerryLiu369/agent-web-search) [![JerryLiu369/agent-web-search MCP server](https://glama.ai/mcp/servers/JerryLiu369/agent-web-search/badges/score.svg)](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) [![artemchuikin/youtube-mcp MCP server](https://glama.ai/mcp/servers/artemchuikin/youtube-mcp/badges/score.svg)](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.
- [jlucasmcrell/apify-scrapers](https://github.com/jlucasmcrell/apify-scrapers) 🐍 🏠 - Model Context Protocol server exposing verified public data scrapers and lead extractors for Google Maps, Glassdoor, SEC EDGAR, and state contractor registries. Run locally via Python stdio.
- [Newscatcher/catchall-mcp](https://github.com/Newscatcher/catchall-mcp) [![Newscatcher/catchall-mcp MCP server](https://glama.ai/mcp/servers/Newscatcher/catchall-mcp/badges/score.svg)](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) [![igorsaevets/page2ai-mcp MCP server](https://glama.ai/mcp/servers/igorsaevets/page2ai-mcp/badges/score.svg)](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) [![pgalyen1987/gate402-mcp MCP server](https://glama.ai/mcp/servers/pgalyen1987/gate402-mcp/badges/score.svg)](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`.
@@ -3502,7 +3503,6 @@ Tools for conducting research, surveys, interviews, and data collection.
- [smeet666/mcp-ptitchef](https://github.com/smeet666/mcp-ptitchef) [![smeet666/mcp-ptitchef MCP server](https://glama.ai/mcp/servers/smeet666/mcp-ptitchef/badges/score.svg)](https://glama.ai/mcp/servers/smeet666/mcp-ptitchef) 📇 ☁️ 🍎 🪟 🐧 - Search Ptitchef, browse its tree of ingredient categories, read a recipe with its ingredients, method, cost and nutrition, and ask what can be cooked from what is in the fridge. Rescales to any number of servings, and lists the other languages a recipe was published in. No API key. `npx -y mcp-ptitchef`
- [smeet666/mcp-bbc-goodfood](https://github.com/smeet666/mcp-bbc-goodfood) [![smeet666/mcp-bbc-goodfood MCP server](https://glama.ai/mcp/servers/smeet666/mcp-bbc-goodfood/badges/score.svg)](https://glama.ai/mcp/servers/smeet666/mcp-bbc-goodfood) 📇 ☁️ 🍎 🪟 🐧 - Search BBC Good Food and read a recipe in either of the two renditions the site writes, its own and the one restated for readers in the United States. Publishes the vocabulary each search facet accepts, since the site answers a value it does not know with a total of zero. Rescales to any number of people. No API key. `npx -y mcp-bbc-goodfood`
- [smeet666/mcp-supertoinette](https://github.com/smeet666/mcp-supertoinette) [![smeet666/mcp-supertoinette MCP server](https://glama.ai/mcp/servers/smeet666/mcp-supertoinette/badges/score.svg)](https://glama.ai/mcp/servers/smeet666/mcp-supertoinette) 📇 ☁️ 🍎 🪟 🐧 - Read Supertoinette's French recipes: ingredients with the quantity separated from the line, steps, difficulty, cost level, resting time, and the five wines the site ranks for a dish. Rescales any recipe to a number of people, saying on each line whether the arithmetic landed exactly. No API key. `npx -y mcp-supertoinette`
### 🔒 <a name="security"></a>Security
- [felixpg13-glitch/spendshield](https://github.com/felixpg13-glitch/spendshield) [![felixpg13-glitch/spendshield MCP server](https://glama.ai/mcp/servers/felixpg13-glitch/spendshield/badges/score.svg)](https://glama.ai/mcp/servers/felixpg13-glitch/spendshield) 🐍 🏠 - Payment guardrails for AI agents: spend-capped digital identity (KYA), dry-run / budget / amount-limit / approval gates, prompt-injection defense (new recipients & large amounts require human sign-off), AES-encrypted secret vault with audited access, full audit trail. Python library + stdio MCP server. `pip install spendshield`