io.github.spences10/mcp-omnisearch MCP Server
io.github.spences10/mcp-omnisearch
Unified web search, AI answers, GitHub code search, and web extraction across Tavily, Brave, Kagi, Exa, Linkup, and Firecrawl.
What this kind of tool is for
- Let your agent search the web or a document set and cite what it found.
- Pull structured facts out of pages instead of copy-pasting by hand.
- Track changes on a topic over days without re-reading everything.
How to compare servers like this
- Source coverage:
- Check which engines, sites, or document types the tool can actually reach.
- Citation behavior:
- Prefer tools that return links you can open, not just summarized claims.
- Terms of service:
- Some sources forbid automated access; make sure the tool stays inside them.
- Maintenance signal:
- Scrapers break silently when pages change; recent commits are the best proxy.
This page carries your copy-paste config: pick your MCP client in the install section on this page and use the copy button.
What is the io.github.spences10/mcp-omnisearch MCP server?
The mcp-omnisearch MCP server provides unified access to multiple search and web extraction providers (Tavily, Brave, Kagi, Exa AI, GitHub, Linkup, and Firecrawl) through four consolidated tools. It consolidates web search, AI-powered answers, GitHub code search, and web content extraction into a single interface for LLMs.
mcp-omnisearch lets you search the web, get AI-sourced answers, search GitHub repositories and code, and extract or summarize web content—all through a single MCP server that supports multiple providers. Choose your preferred provider for each task based on your API keys and use case.
How to install io.github.spences10/mcp-omnisearch
Copy-paste configuration for popular MCP clients.
{
"mcpServers": {
"mcp-omnisearch": {
"command": "npx",
"args": [
"-y",
"mcp-omnisearch"
]
}
}
}Tools & capabilities
Tools this server exposes to the agent.
web_search— Search the web using Tavily, Brave, Kagi, Exa, or Kagi Enrichment with customizable query and result limits.ai_search— Get sourced AI answers using Kagi FastGPT, Exa Answer, or Linkup.github_search— Search GitHub code, repositories, or users with support for GitHub search operators.web_extract— Extract, crawl, scrape, summarize, or find similar content from URLs using Tavily, Kagi, Firecrawl, or Exa.
Use cases
- Search the web across multiple providers and compare results from Brave, Kagi, or Tavily
- Get AI-powered answers with citations from Kagi FastGPT or Exa Answer
- Search GitHub repositories and code files with advanced search operators
- Extract and summarize long articles or web pages without visiting them directly
- Find similar content or crawl websites for structured data extraction
io.github.spences10/mcp-omnisearch MCP server FAQ
It's an MCP server that unifies web search, AI answers, GitHub search, and web extraction across seven different providers (Tavily, Brave, Kagi, Exa, GitHub, Linkup, Firecrawl) into four tools.
The server itself is free and open-source (MIT License), but most providers require paid API keys. You can configure only the providers you have keys for.
Use `npx mcpick add --name mcp-omnisearch --command npx --args=-y,mcp-omnisearch` or manually configure it in your MCP settings with the server command and environment variables for your API keys.
Optional keys for: Tavily, Kagi, Brave, GitHub, Exa, Linkup, and Firecrawl. Providers without keys are skipped; the rest continue working.
Yes. The server gracefully skips providers without API keys and keeps the others functional.
Support varies by provider. See the provider-selection and search-operators documentation for detailed capability matrices and tested examples.
README (reference)
Source of truth, from the repository.
mcp-omnisearch
A Model Context Protocol (MCP) server that provides unified access to Tavily, Brave, Kagi, Exa AI, GitHub, Linkup, and Firecrawl through four consolidated tools.
<a href="https://glama.ai/mcp/servers/gz5wgmptd8"> <img width="380" height="200" src="https://glama.ai/mcp/servers/gz5wgmptd8/badge" alt="Glama badge" /> </a>Quick start
Install the published server with MCPick:
npx mcpick add \
--name mcp-omnisearch \
--command npx \
--args=-y,mcp-omnisearch
MCPick defaults to Claude Code. Use --client and --scope to target
another client or add the server to the current repository:
npx mcpick add \
--name mcp-omnisearch \
--command npx \
--args=-y,mcp-omnisearch \
--client vscode \
--scope project
See Deployment for secret-safe provider-key setup and the supported clients.
To run from source instead:
pnpm install
pnpm run build
node ./dist/index.js
You can also configure the server manually with whichever provider keys you have. Providers without keys are skipped and the rest keep working.
{
"mcpServers": {
"mcp-omnisearch": {
"command": "node",
"args": ["/path/to/mcp-omnisearch/dist/index.js"],
"env": {
"TAVILY_API_KEY": "your-tavily-key",
"KAGI_API_KEY": "your-kagi-key",
"BRAVE_API_KEY": "your-brave-key",
"GITHUB_API_KEY": "your-github-token",
"EXA_API_KEY": "your-exa-key",
"LINKUP_API_KEY": "your-linkup-key",
"FIRECRAWL_API_KEY": "your-firecrawl-key"
}
}
}
}
Tools
web_search
Search the web with Tavily, Brave, Kagi, Exa, or Kagi Enrichment.
{
"query": "sveltekit remote functions site:docs.svelte.dev",
"provider": "brave",
"limit": 10
}
ai_search
Get sourced AI answers with Kagi FastGPT, Exa Answer, or Linkup.
{
"query": "Explain the differences between REST and GraphQL",
"provider": "kagi_fastgpt"
}
github_search
Search GitHub code, repositories, or users.
{
"query": "filename:remote.ts @sveltejs/kit",
"search_type": "code",
"limit": 5
}
web_extract
Extract, crawl, scrape, summarize, or find similar content with Tavily, Kagi, Firecrawl, or Exa.
{
"url": "https://example.com/long-article",
"provider": "kagi",
"mode": "summarize"
}
Documentation
- Provider selection — choose providers by task, key, mode, and capability.
- Search operators — operator support matrix and tested examples.
- Large results — inline vs file response behavior and remote deployment caveats.
- Deployment — MCP client, WSL, and Firecrawl setup.
- Troubleshooting — keys, access, validation, rate limits, and common failures.
Environment variables
TAVILY_API_KEYKAGI_API_KEYBRAVE_API_KEYGITHUB_API_KEYEXA_API_KEYLINKUP_API_KEYFIRECRAWL_API_KEYFIRECRAWL_BASE_URLoptional, for self-hosted FirecrawlOMNISEARCH_LARGE_RESULT_MODEoptional,filedefault orinline
Development
pnpm install
pnpm run build
pnpm test
Please read CONTRIBUTING.md before opening a PR.
License
MIT License - see LICENSE.
Acknowledgments
Built on Model Context Protocol, Tavily, Kagi, Brave Search, Exa AI, Linkup, and Firecrawl.
Related MCP servers
Safe, local SQLite database operations for MCP clients with read, write, schema, and transaction tools.
Query and manage Turso SQLite databases directly from Claude and other LLMs with secure read/write separation.
GTM tools for agents: social listening, traffic and SEO research, lead and creator discovery
Trademark clearance (USPTO+TMview) and self-graded stock signals for AI agents. JSON verdicts.
Verifiable crypto signals, recorded history and always-on monitoring for AI agents via x402 on Base.
Calibrated world model for AI agents. 40 tools: world state, markets, trading. Kalshi + Polymarket.
View repository →



