mcp-omnisearch
by spences10
A Model Context Protocol (MCP) server that provides unified access to multiple search providers and AI tools. It combines the capabilities of Tavily, Perplexity, Kagi, Jina AI, Brave, and Firecrawl to offer comprehensive search, AI responses, content processing, and enhancement features through a single interface.
Last updated: N/A
What is mcp-omnisearch?
MCP Omnisearch is a server that aggregates multiple search providers and AI tools into a single interface, providing comprehensive search, AI responses, content processing, and enhancement features.
How to use mcp-omnisearch?
Configure the server with the necessary API keys for the desired providers (Tavily, Perplexity, Kagi, Jina AI, Brave, Firecrawl) via environment variables or configuration files. Then, use the MCP client to send requests to the server, specifying the desired tool and parameters as outlined in the API documentation.
Key features of mcp-omnisearch
Unified access to multiple search providers (Tavily, Brave, Kagi)
AI response generation with Perplexity AI and Kagi FastGPT
Content processing tools like Jina AI Reader, Kagi Universal Summarizer, and Tavily Extract
Deep crawling and data extraction with Firecrawl
Flexible API key requirements - only enable providers with available keys
Search operators and domain filtering capabilities
Content enhancement tools like Kagi Enrichment API and Jina AI Grounding
Use cases of mcp-omnisearch
Comprehensive web research combining multiple search engines
Generating AI responses with real-time web search integration
Extracting and summarizing content from web pages
Verifying statements against web knowledge
Building custom search and AI applications
Automated data extraction and web crawling
Enhancing content with specialized indexes
FAQ from mcp-omnisearch
Do I need API keys for all providers?
Do I need API keys for all providers?
No, the server automatically detects which API keys are available and only enables those providers.
How do I configure the server?
How do I configure the server?
The server requires configuration through your MCP client. Examples for Cline and Claude Desktop with WSL are provided in the README.
What search operators are supported?
What search operators are supported?
Brave and Kagi support operators like site:, -site:, filetype:, intitle:, inurl:, before:, after:, and exact phrases. Tavily supports domain filtering through API parameters.
How does the server handle rate limits?
How does the server handle rate limits?
The server will handle rate limit errors gracefully and return appropriate error messages.
Where can I find the API documentation?
Where can I find the API documentation?
The API section of the README provides details on the available tools and their parameters.