MCP Omnisearch MCP Server

MCP server for integrating Omnisearch with LLMs

Remote serverstreamable-http

What is the MCP Omnisearch MCP server?

MCP Omnisearch MCP server is a hosted integration for AI assistants that speak the Model Context Protocol. MCP server for integrating Omnisearch with LLMs.

What you get

A Model Context Protocol (MCP) server that provides unified access to Tavily, Brave, Kagi, Exa AI, GitHub, Linkup, and Firecrawl through four consolidated tools.

What the assistant can call

Once MCP Omnisearch is connected, these are the calls the assistant has available:

  • 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 — The github_search tool exposed by this server
  • web_extract — Extract, crawl, scrape, summarize, or find similar content with Tavily, Kagi, Firecrawl, or Exa

Configuration and credentials

You will need 8 environment variables: TAVILY_API_KEY, KAGI_API_KEY, BRAVE_API_KEY, GITHUB_API_KEY, EXA_API_KEY, LINKUP_API_KEY, FIRECRAWL_API_KEY, FIRECRAWL_BASE_URL. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.

Setting it up

Being a remote server, there is no local install. You register the endpoint with your client, authorise it once, and the tools appear.

Choosing this one

Among the search and retrieval options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. MCP Omnisearch's toolset — web_search, ai_search, github_search and 1 more — is a fair guide to whether it matches your workflow. It is maintained by spences10; worth a glance at recent repository activity before you build anything load-bearing on it.

SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.

Before you rely on it

  • Your data travels to the provider's service, so the usual questions apply about what you send and what they retain.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the mcp omnisearch mcp server does with a few real requests.

Available tools

ToolWhat it does
web_searchSearch the web with Tavily, Brave, Kagi, Exa, or Kagi Enrichment.
ai_searchGet sourced AI answers with Kagi FastGPT, Exa Answer, or Linkup.
github_searchThe github_search tool exposed by this server.
web_extractExtract, crawl, scrape, summarize, or find similar content with Tavily, Kagi, Firecrawl, or Exa.

How to install the MCP Omnisearch MCP server

{
  "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.

Configuration

VariableDescriptionRequired
TAVILY_API_KEYCredential the server authenticates with.Yes
KAGI_API_KEYCredential the server authenticates with.Yes
BRAVE_API_KEYCredential the server authenticates with.Yes
GITHUB_API_KEYCredential the server authenticates with.Yes
EXA_API_KEYCredential the server authenticates with.Yes
LINKUP_API_KEYCredential the server authenticates with.Yes
FIRECRAWL_API_KEYCredential the server authenticates with.Yes
FIRECRAWL_BASE_URLEndpoint or connection string the server talks to.Yes

Example prompts to try

  • Use MCP Omnisearch to web search.
  • Use MCP Omnisearch to ai search.
  • Use MCP Omnisearch to github search.

Frequently asked questions

It connects MCP Omnisearch to MCP-compatible AI assistants such as Claude and Cursor, exposing 4 tools (web_search, ai_search, github_search, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with MCP Omnisearch directly.