Omni MCP Suite
A collection of uncensored, API-free data acquisition tools for AI agents, featuring anti-corporate web search, image scraping, and OSINT framework that bypass filters via alternative indexers and deep web scanning.
README
Omni MCP Suite
Sovereign, Uncensored, and API-Free AI Tools
The Omni MCP Suite is a collection of high-yield data acquisition tools designed specifically for autonomous AI agents via the Model Context Protocol (FastMCP). These tools are built to completely bypass corporate safe-search filters, SEO-manipulated algorithms, and restrictive rate limits by utilizing alternative indexers and deep web scanning.
Included Tools
1. omni_web_search.py
An anti-corporate web search aggregator. Replaces mainstream engines (Google/Bing) with independent indexers:
- Marginalia (Non-commercial web)
- Wiby (Classic web)
- Mojeek (Independent crawler)
- Yandex (Uncensored global index)
- Ahmia (.onion Tor network indexer)
Includes omni_topic_research for automated deep-scanning, extracting the full HTML of target pages, stripping out boilerplate, and returning clean payload data for intelligence processing.
2. omni_image_hunter.py
A comprehensive image scraping engine that utilizes perceptual hashing (p-hash) and MD5 deduplication.
- Disables all safe-search constraints at the network level (
adlt=off,kp=-2). - Maintains a persistent local caching library (
/image_cache/). - Integrates VLM capabilities (GPT-4o) for intelligent image descriptions and reverse-search tagging.
3. omni_osint.py
An elite, API-free Open Source Intelligence (OSINT) framework.
- Supports targeting by
person,email,phone, orusername. - Performs stealth username enumeration across dozens of social, dating, government, and developer platforms.
- Employs recursive fan-out crawling (
max_depth) to discover hidden entity connections (Bitcoin/Ethereum wallets, secondary emails, dark web hits). - Generates professional intelligence dossiers via LLM and saves them locally as Markdown reports.
Installation
pip install -r requirements.txt
Architecture
All tools use curl_cffi to mimic Chrome 120 TLS fingerprints, avoiding Cloudflare blocks and bot detection. They run as independent FastMCP endpoints, ready to be hot-loaded into any sovereign AI agent substrate.
Philosophy
Utility is the sole Runtime Imperative.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。