spences10/mcp-omnisearch

🔍 A Model Context Protocol (MCP) server providing unified access to multiple search engines (Tavily, Brave, Kagi, Exa), AI tools (Kagi FastGPT, Exa, Linkup), and content extraction services (Firecrawl, Tavily, Kagi). Includes GitHub search. All through a single interface.

What it solves

It eliminates the need to configure multiple individual search and scraping tools for AI assistants. Instead of managing separate integrations for various search engines and data extraction services, it provides a single, unified interface to access several high-quality web and code search providers.

How it works

It acts as a Model Context Protocol (MCP) server that consolidates multiple external APIs into four primary tools: web_search (for general web searches), ai_search (for sourced AI-generated answers), github_search (for searching code and repositories), and web_extract (for scraping and crawling content). Users provide API keys for the services they wish to use, and the server handles the routing and parameter mapping for providers like Tavily, Brave, Kagi, Exa AI, GitHub, Linkup, and Firecrawl.

Who it’s for

Developers and users of MCP-compatible AI clients (such as Claude Code or VS Code) who want their AI agents to have robust, multi-provider capabilities for searching the web, researching topics, and extracting page content.

Highlights

  • Unified Access: Consolidates Tavily, Brave, Kagi, Exa AI, GitHub, Linkup, and Firecrawl into one server.
  • Diverse Search Modes: Supports standard web search, AI-powered research answers, and GitHub-specific code/user searches.
  • Content Extraction: Includes tools for crawling and scraping web pages into formats like Markdown.
  • Flexible Configuration: Allows users to skip providers they don't have keys for without breaking the rest of the system.

Related

  • Project
    firecrawl/firecrawl-mcp-server

    An MCP server that integrates Firecrawl's web scraping and search capabilities into AI agents, enabling them to search, scrape, and interact with the live web for real-time context.

  • Project
    exa-labs/exa-mcp-server

    An MCP server that connects AI agents to Exa for web search, content fetching, and multi-step research.

  • Project
    brightdata/brightdata-mcp

    An MCP server that gives AI agents real-time web access with built-in bot detection bypass and 69 tools for web search, scraping, and structured data extraction.

  • Project
    tavily-ai/tavily-mcp

    Tavily MCP is a Model Context Protocol server that exposes four web‑knowledge tools—search, extract, map, and crawl—so LLM‑based agents (Claude Code, Cursor, etc.) can fetch up‑to‑date web data, pull page content, generate site maps, or bulk‑crawl sites. It can be used via Tavily’s hosted endpoint or run locally with a single `npx` command, authenticating with an API key or optional OAuth. Configuration is done through environment variables (`TAVILY_API_KEY`, `DEFAULT_PARAMETERS`, `TAVILY_HUMAN_ID`). The server enables real‑time web access for AI assistants, RAG pipelines, and productivity tools without custom scraping code.

  • Project
    1mcp-app/agent

    A unified runtime for MCP servers that aggregates multiple servers into one process and provides a progressive discovery workflow to prevent agent context sprawl.