mcp-omnisearch

mcp-omnisearch

A Model Context Protocol (MCP) server that provides unified access tomultiple search providers and AI tools. This server combines thecapabilities of Tavily, Perplexity, Kagi, Jina AI, Brave, andFirecrawl to offer comprehensive search, AI responses, contentprocessing, and enhancement features through a single interface.

Features

🔍 Search Tools

• Tavily Search: Optimized for factual information with strongcitation support
• Brave Search: Privacy-focused search with good technical contentcoverage
• Kagi Search: High-quality search results with minimaladvertising influence, focused on authoritative sources

🤖 AI Response Tools

• Perplexity AI: Advanced response generation combining real-timeweb search with GPT-4 Omni and Claude 3
• Kagi FastGPT: Quick AI-generated answers with citations (900mstypical response time)

📄 Content Processing Tools

• Jina AI Reader: Clean content extraction with image captioningand PDF support
• Kagi Universal Summarizer: Content summarization for pages,videos, and podcasts
• Tavily Extract: Extract raw content from single or multiple webpages with configurable extraction depth ('basic' or 'advanced').Returns both combined content and individual URL content, withmetadata including word count and extraction statistics
• Firecrawl Scrape: Extract clean, LLM-ready data from single URLswith enhanced formatting options
• Firecrawl Crawl: Deep crawling of all accessible subpages on awebsite with configurable depth limits
• Firecrawl Map: Fast URL collection from websites forcomprehensive site mapping
• Firecrawl Extract: Structured data extraction with AI usingnatural language prompts
• Firecrawl Actions: Support for page interactions (clicking,scrolling, etc.) before extraction for dynamic content

🔄 Enhancement Tools

• Kagi Enrichment API: Supplementary content from specializedindexes (Teclis, TinyGem)
• Jina AI Grounding: Real-time fact verification against webknowledge

Flexible API Key Requirements

MCP Omnisearch is designed to work with the API keys you haveavailable. You don't need to have keys for all providers - the serverwill automatically detect which API keys are available and only enablethose providers.

For example:

• If you only have a Tavily and Perplexity API key, only thoseproviders will be available
• If you don't have a Kagi API key, Kagi-based services won't beavailable, but all other providers will work normally
• The server will log which providers are available based on the APIkeys you've configured

This flexibility makes it easy to get started with just one or twoproviders and add more as needed.

Configuration

This server requires configuration through your MCP client. Here areexamples for different environments:

Cline Configuration

Add this to your Cline MCP settings:

{
	"mcpServers": {
		"mcp-omnisearch": {
			"command": "node",
			"args": ["/path/to/mcp-omnisearch/dist/index.js"],
			"env": {
				"TAVILY_API_KEY": "your-tavily-key",
				"PERPLEXITY_API_KEY": "your-perplexity-key",
				"KAGI_API_KEY": "your-kagi-key",
				"JINA_AI_API_KEY": "your-jina-key",
				"BRAVE_API_KEY": "your-brave-key",
				"FIRECRAWL_API_KEY": "your-firecrawl-key"
			},
			"disabled": false,
			"autoApprove": []
		}
	}
}

Claude Desktop with WSL Configuration

For WSL environments, add this to your Claude Desktop configuration:

{
	"mcpServers": {
		"mcp-omnisearch": {
			"command": "wsl.exe",
			"args": [
				"bash",
				"-c",
				"TAVILY_API_KEY=key1 PERPLEXITY_API_KEY=key2 KAGI_API_KEY=key3 JINA_AI_API_KEY=key4 BRAVE_API_KEY=key5 FIRECRAWL_API_KEY=key6 node /path/to/mcp-omnisearch/dist/index.js"
			]
		}
	}
}

Environment Variables

The server uses API keys for each provider. You don't need keys forall providers - only the providers corresponding to your availableAPI keys will be activated:

• TAVILY_API_KEY: For Tavily Search
• PERPLEXITY_API_KEY: For Perplexity AI
• KAGI_API_KEY: For Kagi services (FastGPT, Summarizer, Enrichment)
• JINA_AI_API_KEY: For Jina AI services (Reader, Grounding)
• BRAVE_API_KEY: For Brave Search
• FIRECRAWL_API_KEY: For Firecrawl services (Scrape, Crawl, Map,Extract, Actions)

You can start with just one or two API keys and add more later asneeded. The server will log which providers are available on startup.

API

The server implements MCP Tools organized by category:

Search Tools

search_tavily

Search the web using Tavily Search API. Best for factual queriesrequiring reliable sources and citations.

Parameters:

• query (string, required): Search query

Example:

{
	"query": "latest developments in quantum computing"
}

search_brave

Privacy-focused web search with good coverage of technical topics.

Parameters:

• query (string, required): Search query

Example:

{
	"query": "rust programming language features"
}

search_kagi

High-quality search results with minimal advertising influence. Bestfor finding authoritative sources and research materials.

Parameters:

• query (string, required): Search query
• language (string, optional): Language filter (e.g., "en")
• no_cache (boolean, optional): Bypass cache for fresh results

Example:

{
	"query": "latest research in machine learning",
	"language": "en"
}

AI Response Tools

ai_perplexity

AI-powered response generation with real-time web search integration.

Parameters:

• query (string, required): Question or topic for AI response

Example:

{
	"query": "Explain the differences between REST and GraphQL"
}

ai_kagi_fastgpt

Quick AI-generated answers with citations.

Parameters:

• query (string, required): Question for quick AI response

Example:

{
	"query": "What are the main features of TypeScript?"
}

Content Processing Tools

process_jina_reader

Convert URLs to clean, LLM-friendly text with image captioning.

Parameters:

• url (string, required): URL to process

Example:

{
	"url": "https://example.com/article"
}

process_kagi_summarizer

Summarize content from URLs.

Parameters:

• url (string, required): URL to summarize

Example:

{
	"url": "https://example.com/long-article"
}

process_tavily_extract

Extract raw content from web pages with Tavily Extract.

Parameters:

• url (string | string[], required): Single URL or array of URLs toextract content from
• extract_depth (string, optional): Extraction depth - 'basic'(default) or 'advanced'

Example:

{
	"url": [
		"https://example.com/article1",
		"https://example.com/article2"
	],
	"extract_depth": "advanced"
}

Response includes:

• Combined content from all URLs
• Individual raw content for each URL
• Metadata with word count, successful extractions, and any failedURLs

firecrawl_scrape_process

Extract clean, LLM-ready data from single URLs with enhancedformatting options.

Parameters:

• url (string | string[], required): Single URL or array of URLs toextract content from
• extract_depth (string, optional): Extraction depth - 'basic'(default) or 'advanced'

Example:

{
	"url": "https://example.com/article",
	"extract_depth": "basic"
}

Response includes:

• Clean, markdown-formatted content
• Metadata including title, word count, and extraction statistics

firecrawl_crawl_process

Deep crawling of all accessible subpages on a website withconfigurable depth limits.

Parameters:

• url (string | string[], required): Starting URL for crawling
• extract_depth (string, optional): Extraction depth - 'basic'(default) or 'advanced' (controls crawl depth and limits)

Example:

{
	"url": "https://example.com",
	"extract_depth": "advanced"
}

Response includes:

• Combined content from all crawled pages
• Individual content for each page
• Metadata including title, word count, and crawl statistics

firecrawl_map_process

Fast URL collection from websites for comprehensive site mapping.

Parameters:

• url (string | string[], required): URL to map
• extract_depth (string, optional): Extraction depth - 'basic'(default) or 'advanced' (controls map depth)

Example:

{
	"url": "https://example.com",
	"extract_depth": "basic"
}

Response includes:

• List of all discovered URLs
• Metadata including site title and URL count

firecrawl_extract_process

Structured data extraction with AI using natural language prompts.

Parameters:

• url (string | string[], required): URL to extract structured datafrom
• extract_depth (string, optional): Extraction depth - 'basic'(default) or 'advanced'

Example:

{
	"url": "https://example.com",
	"extract_depth": "basic"
}

Response includes:

• Structured data extracted from the page
• Metadata including title, extraction statistics

firecrawl_actions_process

Support for page interactions (clicking, scrolling, etc.) beforeextraction for dynamic content.

Parameters:

• url (string | string[], required): URL to interact with andextract content from
• extract_depth (string, optional): Extraction depth - 'basic'(default) or 'advanced' (controls complexity of interactions)

Example:

{
	"url": "https://news.ycombinator.com",
	"extract_depth": "basic"
}

Response includes:

• Content extracted after performing interactions
• Description of actions performed
• Screenshot of the page (if available)
• Metadata including title and extraction statistics

Enhancement Tools

enhance_kagi_enrichment

Get supplementary content from specialized indexes.

Parameters:

• query (string, required): Query for enrichment

Example:

{
	"query": "emerging web technologies"
}

enhance_jina_grounding

Verify statements against web knowledge.

Parameters:

• statement (string, required): Statement to verify

Example:

{
	"statement": "TypeScript adds static typing to JavaScript"
}

Development

Setup

1. Clone the repository
2. Install dependencies:

pnpm install

3. Build the project:

pnpm run build

4. Run in development mode:

pnpm run dev

Publishing

1. Update version in package.json
2. Build the project:

pnpm run build

3. Publish to npm:

pnpm publish

Troubleshooting

API Keys and Access

Each provider requires its own API key and may have different accessrequirements:

• Tavily: Requires an API key from their developer portal
• Perplexity: API access through their developer program
• Kagi: Some features limited to Business (Team) plan users
• Jina AI: API key required for all services
• Brave: API key from their developer portal
• Firecrawl: API key required from their developer portal

Rate Limits

Each provider has its own rate limits. The server will handle ratelimit errors gracefully and return appropriate error messages.

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

License

MIT License - see the LICENSE file for details.

Acknowledgments

Built on:

• Model Context Protocol
• Tavily Search
• Perplexity AI
• Kagi Search
• Jina AI
• Brave Search
• Firecrawl