mcp-omnisearch
🔍 A Model Context Protocol (MCP) server providing unified access to multiple search engines (Tavily, Brave, Kagi), AI tools (Perplexity, FastGPT), and content processing services (Jina AI, Kagi). Combines search, AI responses, content processing, and enhancement features through a single interface.
claude mcp add --transport stdio spences10-mcp-omnisearch node /path/to/mcp-omnisearch/dist/index.js \ --env EXA_API_KEY="your-exa-api-key" \ --env KAGI_API_KEY="your-kagi-api-key" \ --env BRAVE_API_KEY="your-brave-api-key" \ --env GITHUB_API_KEY="your-github-api-key" \ --env TAVILY_API_KEY="your-tavily-api-key" \ --env JINA_AI_API_KEY="your-jina-ai-api-key" \ --env FIRECRAWL_API_KEY="your-firecrawl-api-key" \ --env FIRECRAWL_BASE_URL="http://localhost:3002" \ --env PERPLEXITY_API_KEY="your-perplexity-api-key"
How to use
MCP Omnisearch provides a single interface to query and orchestrate multiple search providers and AI tools. It exposes a unified API for performing web searches, code searches, and content processing, while also enabling AI-generated responses via Perplexity, Kagi FastGPT, and Exa Answer. Beyond search, it can extract and summarize content with Jina AI, and perform enhanced data collection with Firecrawl. To use it, configure the MCP client with the mcp-omnisearch server name and supply your provider API keys as environment variables. Once configured, you can send queries to the server, which will route requests to the available providers based on your keys and preferences. The server automatically enables only the providers for which you have valid keys, and logs which providers are active.
How to install
Prerequisites:
- Node.js (version 14+)
- npm or pnpm
- Git
-
Clone the repository (or install via your preferred method): git clone https://github.com/Spences10/mcp-omnisearch.git cd mcp-omnisearch
-
Install dependencies: npm install
or
pnpm install
-
Build or prepare the server if a build step exists (follow repository specifics): npm run build
or if dist is provided directly, ensure you point to the built index in dist/index.js
-
Run the server locally (example using Node): node dist/index.js
-
Configure your MCP client (e.g., Cline or Claude Desktop) to point at the server with the proper environment keys as described in the Configuration section.
Additional notes
Tips and common considerations:
- You can enable or disable providers by omitting or including their API keys in the environment configuration. The server will automatically detect available providers.
- Ensure FIRECRAWL_BASE_URL points to your Firecrawl service if you plan to use Firecrawl features.
- For WSL or container deployments, you may need to adjust the command and argument paths to reflect the runtime environment.
- Keep API keys secure; do not commit them to version control.
- If you encounter rate limits or authentication errors, verify the keys and check provider status pages for outages.
- When debugging, check the MCP client logs to confirm which providers are active and how requests are routed.
Related MCP Servers
obsidian -tools
Add Obsidian integrations like semantic search and custom Templater prompts to Claude or any MCP client.
mcp-svelte-docs
🔍 MCP server that lets you search and access Svelte documentation with built-in caching
CanvasMCPClient
Canvas MCP Client is an open-source, self-hostable dashboard application built around an infinite, zoomable, and pannable canvas. It provides a unified interface for interacting with multiple MCP (Model Context Protocol) servers through a flexible, widget-based system.
ClaudeHistoryMCP
MCP server for searching and surfacing Claude Code conversation history
perplexity
A Perplexity API MCP server that unlocks Perplexity's search-augmented AI capabilities for LLM agents. Features robust error handling, secure input validation, and transparent reasoning with the showThinking parameter.
grok-faf
First MCP server for Grok | FAST⚡️AF • URL-based AI context • Vercel-deployed
