mcp-omnisearch
The mcp-omnisearch server provides unified access to multiple search providers and AI tools for comprehensive information retrieval and content processing.
Web Search: Use Tavily (factual queries with citations), Brave (privacy-focused technical content), and Kagi (authoritative sources with minimal ads). Supports domain filtering and various search operators.
AI Response Tools: Generate AI-powered answers using Perplexity AI (real-time web search with GPT-4/Claude 3) and Kagi FastGPT (quick answers with citations).
Content Processing: Extract and analyze content from URLs using Jina AI Reader, Kagi Universal Summarizer, Tavily Extract, and Firecrawl's suite of tools (scraping, crawling, mapping, and structured data extraction). Supports processing single or multiple URLs with configurable extraction depth.
Enhancement Tools: Verify facts with Jina AI Grounding and enrich content with Kagi Enrichment API.
Flexible API Key Requirements: Use only the providers for which you have API keys, making it easy to start small and scale up.
Provides privacy-focused web search capabilities through the Brave Search API, with good coverage of technical topics
Offers high-quality search results with minimal advertising influence, as well as FastGPT for quick AI-generated answers, Universal Summarizer for content summarization, and Enrichment API for supplementary content from specialized indexes
Provides AI-powered response generation with real-time web search integration, combining web search with GPT-4 Omni and Claude 3
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@mcp-omnisearchsearch for recent TypeScript updates on GitHub using filetype:md"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
mcp-omnisearch
A Model Context Protocol (MCP) server that provides unified access to Tavily, Brave, Kagi, Exa AI, GitHub, Linkup, and Firecrawl through four consolidated tools.
Quick start
pnpm install
pnpm run build
node ./dist/index.jsConfigure the server in your MCP client with whichever provider keys you have. Providers without keys are skipped and the rest keep working.
{
"mcpServers": {
"mcp-omnisearch": {
"command": "node",
"args": ["/path/to/mcp-omnisearch/dist/index.js"],
"env": {
"TAVILY_API_KEY": "your-tavily-key",
"KAGI_API_KEY": "your-kagi-key",
"BRAVE_API_KEY": "your-brave-key",
"GITHUB_API_KEY": "your-github-token",
"EXA_API_KEY": "your-exa-key",
"LINKUP_API_KEY": "your-linkup-key",
"FIRECRAWL_API_KEY": "your-firecrawl-key"
}
}
}
}Related MCP server: MCP Search Server
Tools
web_search
Search the web with Tavily, Brave, Kagi, Exa, or Kagi Enrichment.
{
"query": "sveltekit remote functions site:docs.svelte.dev",
"provider": "brave",
"limit": 10
}ai_search
Get sourced AI answers with Kagi FastGPT, Exa Answer, or Linkup.
{
"query": "Explain the differences between REST and GraphQL",
"provider": "kagi_fastgpt"
}github_search
Search GitHub code, repositories, or users.
{
"query": "filename:remote.ts @sveltejs/kit",
"search_type": "code",
"limit": 5
}web_extract
Extract, crawl, scrape, summarize, or find similar content with Tavily, Kagi, Firecrawl, or Exa.
{
"url": "https://example.com/long-article",
"provider": "kagi",
"mode": "summarize"
}Documentation
Provider selection — choose providers by task, key, mode, and capability.
Search operators — operator support matrix and tested examples.
Large results — inline vs file response behavior and remote deployment caveats.
Deployment — MCP client, WSL, Docker, cloud, and Firecrawl setup.
Troubleshooting — keys, access, validation, rate limits, and common failures.
Environment variables
TAVILY_API_KEYKAGI_API_KEYBRAVE_API_KEYGITHUB_API_KEYEXA_API_KEYLINKUP_API_KEYFIRECRAWL_API_KEYFIRECRAWL_BASE_URLoptional, for self-hosted FirecrawlOMNISEARCH_LARGE_RESULT_MODEoptional,filedefault orinline
Development
pnpm install
pnpm run build
pnpm testPlease read CONTRIBUTING.md before opening a PR.
License
MIT License - see LICENSE.
Acknowledgments
Built on Model Context Protocol, Tavily, Kagi, Brave Search, Exa AI, Linkup, and Firecrawl.
Maintenance
Tools
Latest Blog Posts
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/spences10/mcp-omnisearch'
If you have feedback or need assistance with the MCP directory API, please join our Discord server