Omnisearch MCP Server

A Model Context Protocol (MCP) server that provides unified access to Tavily, Brave, Kagi, Exa AI, GitHub, Linkup, and Firecrawl through four consolidated tools. Its 4 documented tools cluster into web, other, github. It runs locally over stdio via the published package.

People connecting web scraping tools to Claude, Cursor, VS Code, or another MCP client. The project is written in TypeScript.

VERIFIED ACTIVE

LAST COMMIT 2026-08-21 · ★ 345 · #7 OF 78 MAINTAINED WEB SCRAPING · VERIFIED 2026-08-25

MIT · TypeScript servers · how we verify → /methodology

01 · Install Omnisearch

before you install - you'll need

Set TAVILY_API_KEY, KAGI_API_KEY, BRAVE_API_KEY, GITHUB_API_KEY, EXA_API_KEY, LINKUP_API_KEY, FIRECRAWL_API_KEY before connecting.

Claude Code

claude mcp add spences10-mcp-omnisearch -- npx -y mcp-omnisearch

Claude Desktop / Cursor / VS Code - add to config

{
  "mcpServers": {
    "spences10-mcp-omnisearch": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-omnisearch"
      ]
    }
  }
}

Same JSON for Cursor. For VS Code, rename the top-level key from `mcpServers` to `servers`.

Using another client? Same JSON, different key

Claude Desktop · mcpServers

Cursor · mcpServers

VS Code · servers

Windsurf · mcpServers

Zed · context_servers

Cline · mcpServers

Roo Code · mcpServers

Continue · mcpServers

LibreChat · mcpServers

Gemini CLI · mcpServers

Codex CLI · mcp_servers

Full setup guides: every client.

02 · Evidence

Security posture

What to check before giving this server access to your agent - from the registry, GitHub, and our own probes. We don't score safety; we show what's verifiable.

runs as local process (stdio) - runs on your machine with your user's permissions

license MIT - declared in the repository

npm package mcp-omnisearch - unscoped; check the name against the project README before installing

registry namespace io.github.spences10 is GitHub-verified and matches the repo owner

03 · What Omnisearch can do

Prose above is summarized from the project's README and registry record - no invented capabilities.

What you can build

With this server connected, an agent can search the web with Tavily, Brave, Kagi, Exa, or Kagi Enrichment, get sourced AI answers with Kagi FastGPT, Exa Answer, or Linkup, and extract, crawl, scrape, summarize, or find similar content with.

Capability map

Tools grouped from the project's README - what Omnisearch lets an agent do.

Web

2 tools - e.g. Search the web with Tavily, Brave, Kagi, Exa, or Kagi Enrichment.; Extract, crawl, scrape, summarize, or find similar content with

web_search · web_extract

other

1 tool - e.g. Get sourced AI answers with Kagi FastGPT, Exa Answer, or Linkup.

ai_search

Github

1 tool - e.g. Search GitHub code, repositories, or users.

github_search

Latest releases

v0.0.29 · 2026-08-16

What changed · Support the stateless MCP 2026-07-28 protocol, including server discovery and modern request metadata. · Document MCPick installation, project-scoped client configuration, secret-safe provider keys, and…

v0.0.4 · 2025-03-21

04 · Who maintains Omnisearch

mcp-omnisearch is maintained by spences10. We track 3 MCP servers from spences10 - 3 actively maintained, 382 combined GitHub stars, oldest repo from Mar 2025. Full record: all servers from spences10.

05 · Facts

repository: github.com/spences10/mcp-omnisearch
category: web scraping - ranked #7 of 78 actively-maintained web scraping servers as of 2026-08-25.
release cadence: 1 release in the last 90 days (latest 2026-08-16)
registry: io.github.spences10/mcp-omnisearch (active, first published 2025-09-10)
packages: npm:mcp-omnisearch

06 · Omnisearch FAQ

Is Omnisearch still maintained?

Yes - as of 2026-08-25, its last commit was 2026-08-21 and it shipped 1 release in the last 90 days. We re-verify nightly.

What can Omnisearch do?

How do I install Omnisearch?

Run `npx -y mcp-omnisearch`. The README documents 7 environment variables (TAVILY_API_KEY, KAGI_API_KEY, BRAVE_API_KEY…) to set first. Set TAVILY_API_KEY, KAGI_API_KEY, BRAVE_API_KEY, GITHUB_API_KEY, EXA_API_KEY, LINKUP_API_KEY, FIRECRAWL_API_KEY before connecting. You can also paste the ready-made client config above.

Does Omnisearch run locally?

Yes - it's a stdio server: it runs on your machine (via npx) with your user's permissions. Your data stays local unless the server itself calls external APIs.

07 · Alternatives to Omnisearch

Alternatives to Omnisearch

Maintained web scraping servers if Omnisearch isn't the fit.

Pairs well with

Servers that cover what Omnisearch doesn't - only shown when the pairing reason fits the companion.

More web scraping MCP servers · Crawlie · Search1 API · Indonesia Civic Stack · Read GZH

More TypeScript MCP servers · SQLite Tools · Turso Cloud · Interactive Leetcode MCP · Brainstorm MCP · Saga MCP · see all