MCP server for integrating Omnisearch with LLMs
MCP server for integrating Omnisearch with LLMs
A Model Context Protocol (MCP) server that provides unified access to Tavily, Brave, Kagi, Exa AI, GitHub, Linkup, and Firecrawl through four consolidated tools.
Compare MCP servers by category, or browse hosted MCP servers if you prefer an endpoint over a local process.
Check the linked publisher documentation and your connected client's tool list. Names and availability can vary with the server version and account permissions.
| Tool | What it does |
|---|---|
| web_search | Search the web with Tavily, Brave, Kagi, Exa, or Kagi Enrichment. |
| ai_search | Get sourced AI answers with Kagi FastGPT, Exa Answer, or Linkup. |
| github_search | |
| web_extract | Extract, crawl, scrape, summarize, or find similar content with Tavily, Kagi, Firecrawl, or Exa. |
{
"mcpServers": {
"omnisearch": {
"command": "npx",
"args": ["-y", "pnpm"],
"env": {
"TAVILY_API_KEY": "your-value",
"KAGI_API_KEY": "your-value",
"BRAVE_API_KEY": "your-value",
"GITHUB_API_KEY": "your-value",
"EXA_API_KEY": "your-value",
"LINKUP_API_KEY": "your-value",
"FIRECRAWL_API_KEY": "your-value",
"FIRECRAWL_BASE_URL": "your-value"
}
}
}
}Add to claude_desktop_config.json, then restart Claude Desktop.
| Variable | Description | Required |
|---|---|---|
| TAVILY_API_KEY | Credential the server authenticates with. | Yes |
| KAGI_API_KEY | Credential the server authenticates with. | Yes |
| BRAVE_API_KEY | Credential the server authenticates with. | Yes |
| GITHUB_API_KEY | Credential the server authenticates with. | Yes |
| EXA_API_KEY | Credential the server authenticates with. | Yes |
| LINKUP_API_KEY | Credential the server authenticates with. | Yes |
| FIRECRAWL_API_KEY | Credential the server authenticates with. | Yes |
| FIRECRAWL_BASE_URL | Endpoint or connection string the server talks to. | Yes |
Retrieve public web pages as readable Markdown with the reference Fetch MCP server, including pagination for longer responses.
Use Firecrawl MCP to retrieve website content and extract information for research through Firecrawl’s API-backed web tools.
Google News search and topics with the full article text in Markdown for LLMs.
1. **Clone the repository** and install dependencies: ```sh git clone <your-repo-url> cd mcp-server-ollama-deep-researcher npm install ```
A remote Model Context Protocol (MCP) server for the Jina Reader, Search, Embeddings and Reranker APIs:
One API for Search, Crawling, and Sitemaps