Omnisearch
Unifies search and content processing by dynamically selecting optimal providers like Tavily, Brave,...
Decide which providers you want to use
Review the list of supported providers below. For each provider you wish to use, you will need to obtain an API key:- Tavily (
TAVILY_API_KEY) - Perplexity AI (
PERPLEXITY_API_KEY) - Kagi (
KAGI_API_KEY) - Jina AI (
JINA_AI_API_KEY) - Brave (
BRAVE_API_KEY) - GitHub (
GITHUB_API_KEY) - Exa AI (
EXA_API_KEY) - Firecrawl (
FIRECRAWL_API_KEY)
- Tavily (
Obtain API keys for each provider you need
Use the following instructions for each provider:Tavily API Key
- Go to the Tavily Developer Portal.
- Sign up or log in.
- Go to your account dashboard and find the section for API keys.
- Generate a new API key.
Perplexity API Key
- Visit the Perplexity AI site.
- Sign up or log in.
- Access the developer section and follow the process to obtain your API key.
Kagi API Key
- Go to Kagi.com.
- Register or sign in.
- Navigate to your account settings or the API section.
- Generate an API key.
- Note: Some features require a Business (Team) plan.
Jina AI API Key
- Visit Jina AI.
- Sign up or log in.
- Go to the dashboard or developer section and obtain your API key.
Brave API Key
- Go to the Brave Search Developer Portal.
- Create an account or log in.
- Access the API section and copy your API key.
GitHub API Key (Personal Access Token)
- Go to GitHub Personal Access Tokens.
- Click Generate new token → Generate new token (classic).
- Set a name (e.g., "MCP Omnisearch - Public Search").
- Choose an expiration (e.g., 90 days).
- Leave all scopes UNCHECKED (important for public data access only).
- Generate the token and copy it.
- Use this token as your
GITHUB_API_KEY.
Exa AI API Key
- Visit Exa Dashboard.
- Sign up or log in.
- Find the API section and create/copy your API key.
Firecrawl API Key
- Go to the Firecrawl Developer Portal.
- Sign up or log in.
- Locate the API key section and get or create your API key.
(Optional) Set the Firecrawl Base URL
- If you are self-hosting Firecrawl, obtain your instance's base URL (e.g.,
http://localhost:3002). - Otherwise, you may leave
FIRECRAWL_BASE_URLunset to use the default cloud service.
- If you are self-hosting Firecrawl, obtain your instance's base URL (e.g.,
Fill in the API keys in your FastMCP connection interface
- For each provider, enter the corresponding API key in the FastMCP connection setup interface.
- Fill:
TAVILY_API_KEYPERPLEXITY_API_KEYKAGI_API_KEYJINA_AI_API_KEYBRAVE_API_KEYGITHUB_API_KEYEXA_API_KEYFIRECRAWL_API_KEY- (Optional)
FIRECRAWL_BASE_URLif running a self-hosted instance
Note: You do not need keys for all providers. Only the services for which you provide keys will be enabled.
Save the configuration and continue
After entering your API keys, save the configuration to enable the desired providers.
You’re done! Providers with valid keys will become available when using the MCP Omnisearch server.
Quick Start
Choose Connection Type for
Authentication Required
Please sign in to use FastMCP hosted connections
Configure Environment Variables for
Please provide values for the following environment variables:
started!
The MCP server should open in . If it doesn't open automatically, please check that you have the application installed.
Copy and run this command in your terminal:
Make sure Gemini CLI is installed:
Visit Gemini CLI documentation for installation instructions.
Make sure Claude Code is installed:
Visit Claude Code documentation for installation instructions.
Installation Steps:
Configuration
Installation Failed
More for Web Search
View All →
DuckDuckGo
Experience fast and reliable DuckDuckGo web search with this TypeScript MCP server. It offers a simple search interface supporting customizable queries, result counts, and safe search levels. Built-in rate limiting ensures fair usage with up to 1 request per second and 15,000 per month. The server returns well-formatted Markdown results, making it easy to integrate and display search data. Designed to demonstrate core Model Context Protocol concepts, it also includes helpful debugging tools to inspect communication. Perfect for developers wanting seamless DuckDuckGo integration via MCP with efficient error handling and robust controls.
Microsoft Docs
Remote
Access official Microsoft documentation instantly with the Microsoft Learn Docs MCP Server. This cloud service implements the Model Context Protocol (MCP) to enable AI tools like GitHub Copilot and others to perform high-quality semantic searches across Microsoft Learn, Azure, Microsoft 365 docs, and more. It delivers up to 10 concise, context-relevant content chunks in real time, ensuring up-to-date, accurate information. Designed for seamless integration with any MCP-compatible client, it helps AI assistants ground their responses in authoritative, current Microsoft resources for better developer support and productivity.
Brave Search
Integrate web search and local search capabilities with Brave. Brave Search allows you to seamlessly integrate Brave Search functionality into AI assistants like Claude. By implementing a Model Context Protocol (MCP) server, it enables the AI to leverage Brave Search's web search and local business search capabilities. It provides tools for both general web searches and specific local searches, enhancing the AI assistant's ability to provide relevant and up-to-date information.
Exa Search
Empower AI assistants like Claude with real-time web data using the Exa MCP Server. This Model Context Protocol server connects AI models to the Exa AI Search API, enabling safe, up-to-date web searches across diverse tools such as academic papers, company data, LinkedIn, Wikipedia, GitHub, and more. Its flexible toolset enhances research, competitor analysis, and content extraction, providing comprehensive information for smarter AI interactions. Designed for seamless integration with Claude Desktop, the Exa MCP Server boosts AI capabilities by delivering fast, reliable, and controlled access to the latest online information.
