A side-by-side look at the Kagimcp and MCP Omnisearch MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.
Verdict: choose Kagimcp for search & data extraction work as a local process; choose MCP Omnisearch for search & data extraction as a local process. You can also run both side by side in one mcpServers block.
KAGI_API_KEY.kagi_search_fetch, kagi_extract.TAVILY_API_KEY, KAGI_API_KEY, BRAVE_API_KEY, GITHUB_API_KEY, EXA_API_KEY, LINKUP_API_KEY, FIRECRAWL_API_KEY, FIRECRAWL_BASE_URL.web_search, ai_search, github_search.Rows where the two servers differ are marked.
| Spec | ||
|---|---|---|
| Category | Search & Data Extraction | Search & Data Extraction |
| Quality signal | 80/100 · Excellent | 60/100 · Good |
| Install command | Confirmed | Confirmed |
| Transport | Local subprocess (stdio) | Local subprocess (stdio) |
| Auth | API key required | Not declared |
| Pricing | BYOK (pay the provider) | Not declared |
| Required env vars | KAGI_API_KEY | TAVILY_API_KEYKAGI_API_KEYBRAVE_API_KEYGITHUB_API_KEYEXA_API_KEYLINKUP_API_KEYFIRECRAWL_API_KEYFIRECRAWL_BASE_URL |
| Verified owner | Verified | Community listing |
| GitHub stars | 544 | 356 |
| Directory activity | 3 views 0 installs 0 upvotes | 1 views 0 installs 0 upvotes |
| Tools | 2 | 4 |
| Full listing | View Kagimcp | View MCP Omnisearch |
kagi_search_fetchFetch web results for a query using the Kagi Search API. Use for general search and when the user explicitly tells you to 'fetch' results/information. Results are numbered so that a user may refer to a result by a specific number.kagi_extractExtract the content of a web page as markdown using the Kagi Extract API. Use this to read the full content of a page when needed.web_searchSearch the web with Tavily, Brave, Kagi, or Exa.ai_searchGet sourced AI answers with Exa Answer, Linkup, or Tavily Research.github_searchSearch GitHub code, repositories, or users.web_extractExtract, crawl, scrape, or find similar content with Tavily,Paste either block (or both) into your client config, e.g. claude_desktop_config.json or ~/.cursor/mcp.json. We only show a config when the install command is confirmed.
{
"mcpServers": {
"kagisearch-kagimcp": {
"command": "uvx",
"args": [
"kagimcp"
],
"env": {
"KAGI_API_KEY": "YOUR_KAGI_API_KEY_HERE"
}
}
}
}
{
"mcpServers": {
"mcp-omnisearch": {
"command": "npx",
"args": [
"-y",
"mcpick"
],
"env": {
"TAVILY_API_KEY": "YOUR_TAVILY_API_KEY_HERE",
"KAGI_API_KEY": "YOUR_KAGI_API_KEY_HERE",
"BRAVE_API_KEY": "YOUR_BRAVE_API_KEY_HERE",
"GITHUB_API_KEY": "YOUR_GITHUB_API_KEY_HERE",
"EXA_API_KEY": "YOUR_EXA_API_KEY_HERE",
"LINKUP_API_KEY": "YOUR_LINKUP_API_KEY_HERE",
"FIRECRAWL_API_KEY": "YOUR_FIRECRAWL_API_KEY_HERE",
"FIRECRAWL_BASE_URL": "YOUR_FIRECRAWL_BASE_URL_HERE"
}
}
}
}