A Model Context Protocol (MCP) server that unifies access to multiple search engines, AI response tools, and content processing services. It targets developers and researchers needing a consolidated interface for diverse information retrieval and processing tasks, offering a flexible way to integrate various data sources without requiring keys for all providers.

How It Works

This project acts as an MCP server, abstracting a wide array of services including search (Tavily, Brave, Kagi, Exa, GitHub), AI responses (Perplexity, Kagi FastGPT, Exa Answer), and content processing (Jina AI, Firecrawl). Its core advantage lies in its flexible API key management; it automatically detects and enables only those providers for which API keys are configured, simplifying setup and allowing users to leverage the services they have access to. The server supports advanced search operators and integrates various content extraction and AI response capabilities through a single, unified interface.

Quick Start & Requirements

• Primary install / run command: Recommended: docker-compose up -d after cloning the repository and creating a .env file with API keys. Direct Docker run is also supported.
• Non-default prerequisites and dependencies: API keys for services like Tavily, Perplexity, Kagi, Jina AI, Brave, GitHub, Exa AI, and Firecrawl are required. A GitHub Personal Access Token with no scopes is necessary for GitHub search functionality.
• Links: Repository: https://github.com/spences10/mcp-omnisearch

Highlighted Details

• Unified Provider Access: Integrates search, AI responses, and content processing from diverse sources like Tavily, Brave, Kagi, Perplexity, Jina AI, Firecrawl, and Exa AI.
• Advanced Search Capabilities: Supports rich native operators for Brave and Kagi, alongside specialized syntax for GitHub code, repository, and user searches.
• Flexible Provider Activation: Automatically enables services based on the presence of corresponding API keys, allowing incremental setup.
• Comprehensive Content Processing: Includes tools for web scraping, summarization, content extraction, site mapping, and AI-driven structured data extraction via services like Firecrawl and Jina AI.

Maintenance & Community

No specific details regarding maintainers, community channels (e.g., Discord, Slack), or a public roadmap are provided in the README. The presence of a CONTRIBUTING.md file suggests a defined process for contributions.

Licensing & Compatibility

• License type: MIT License.
• Compatibility notes: The MIT license generally permits commercial use and integration into closed-source projects. However, users must adhere to the terms of service and API usage policies of the individual underlying providers.

Limitations & Caveats

Functionality is entirely dependent on the user providing valid API keys for the desired services. Some features of Kagi may be restricted to paid plans. GitHub search is subject to API rate limits (5,000 requests/hour for code search). Self-hosted Firecrawl instances require separate setup and configuration.