Vibe Coding Discovermcp-omnisearch
View on GitHub🔍 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.
MCP server exposing four consolidated tools (web_search, ai_search, github_search, web_extract) that unify Tavily, Brave, Kagi, Exa, Linkup, Firecrawl, and GitHub behind one interface. Providers without API keys are skipped, so it works with whatever keys you have.
Use Cases
Give LLM agents unified web search across multiple providersReturn sourced AI answers via Kagi FastGPT, Exa Answer, Linkup, or Tavily ResearchSearch GitHub code, repositories, and users from an agentExtract, crawl, scrape, and summarize web pages into markdownSite mapping and similar-content discovery for researchEnrich RAG pipelines with fresh web contentFact verification and research report generation for agentsSelf-hosted Firecrawl content extractionSearch news with topic and time-range filters
Built With
- Language
- TypeScript
- Frameworks
- tmcp · valibot · @tmcp/transport-stdio · @tmcp/adapter-valibot · octokit · vitest · vite-plus · node.js
Tags
mcp · model-context-protocol · web-search · ai-search · content-extraction · web-scraping · crawling · github-search · tavily · brave · kagi · exa · firecrawl · linkup · typescript · multi-provider