AI and models · Independent · 22 Oct 2026

spences10/mcp-omnisearch

πŸ” A Model Context Protocol (MCP) server providing unified access to multiple search engines (Tavily, Brave, Kagi, Exa), AI tools (Kagi FastGPT, Exa, Linkup), and content extraction services (Firecrawl, Tavily, Kagi). Includes GitHub search. All through a single interface.

← AI and models
mcp-omnisearch: unified search for AI. Brings multiple search engines to your AI assistant.

In simple English

When you ask an AI assistant a question, it often needs to look up information online. This tool gives your assistant access to several different search engines and web scrapers at the same time. You can search the regular web, find code on GitHub, or extract clean text from messy web pages. It bundles all these services into four simple tools that any Model Context Protocol (a standard way for AI assistants to talk to external tools and data sources) client can use. You only need to provide API keys (a secret password that lets your program talk to an external service) for the specific search providers you want to use.

What it is

A TypeScript (a programming language that adds strict rules to JavaScript) server that implements the Model Context Protocol to unify multiple search, AI answer, and web scraping providers. It exposes four consolidated tools for web search, AI-powered search, GitHub searches, and webpage content extraction.

What it is good for

Solo builders who want their local AI coding assistant or chat client to search across different engines like Brave, Tavily, Kagi, Exa, and GitHub without configuring each one separately.

Stars357
LicenceMIT
Latestv0.2.1 (2026-10-11)checked 22 Oct 2026
Last code change2026-10-21
Written inTypeScript
Setup effort
2 / 5
Payoff
4 / 5
Good
  • Combines seven popular search, AI answer, and scraping services into one interface.
  • Works even if you only have an API key for one or two of the supported providers.
  • Easy installation with npx or MCPick.
Watch for
  • Requires individual API keys for the paid or freemium search providers you want to use.
  • Node.js environment required to run the server.
  • Depends on third-party search APIs remaining online and unchanged.
Replaces

configuring multiple separate search tool integrations for your AI assistant

Works well with

Claude Code

Similar repositories
Also reviewed on Repo Radar
  • ggml-org/llama.cpp132k stars

    A C and C++ library and command-line tool for running language models locally.

  • EleutherAI/lm-evaluation-harness14k stars

    Runs standard question sets against a language model and reports the scores.

  • mudler/LocalAI50k stars

    Serves text, vision, speech, image and video models from one self-hosted service that imitates the paid interfaces.

Install
npx mcpick add \
  --name mcp-omnisearch \
  --command npx \
  --args=-y,mcp-omnisearch

Independent: reviewed for Repo Radar outside the daily editions. Every independent repository

On Stack Radar: Data & Research β€Ί Web Scraping & Crawling β€Ί Search APIs for AI Agents.

Get the next edition in your inbox

A dozen repositories, opened and checked. The licence read, the last release dated, and the ones that did not make it named with the reason. It is the half most lists leave out.

No tracking pixels. One click to leave. The archive stays free either way.

We use your address to send the edition and nothing else. Confirm by email, leave in one click. How we handle it.