tavily-mcp and one-search-mcp

These are competitors—both provide web search and scraping capabilities, though Tavily-MCP offers a specialized production implementation while OneSearch-MCP provides a multi-backend abstraction layer supporting various search providers (SearXNG, Tavily, DuckDuckGo, Bing).

tavily-mcp
77
Verified
one-search-mcp
63
Established
Maintenance 20/25
Adoption 10/25
Maturity 25/25
Community 22/25
Maintenance 10/25
Adoption 9/25
Maturity 25/25
Community 19/25
Stars: 1,498
Forks: 215
Downloads:
Commits (30d): 8
Language: JavaScript
License: MIT
Stars: 87
Forks: 18
Downloads:
Commits (30d): 0
Language: TypeScript
License: MIT
No risk flags
No risk flags

About tavily-mcp

tavily-ai/tavily-mcp

Production ready MCP server with real-time search, extract, map & crawl.

Provides four specialized web tools—search, extract, map, and crawl—integrated via the Model Context Protocol for seamless AI assistant connectivity. Supports both local deployment (Node.js-based) and remote hosting via Tavily's hosted MCP endpoint, with flexible authentication through API keys or OAuth. Integrates directly with Claude Desktop, Cursor, and Claude Code via HTTP transport with configurable default parameters.

About one-search-mcp

yokingma/one-search-mcp

🚀 OneSearch MCP Server: Web Search & Scraper & Extract, Support agent-browser, SearXNG, Tavily, DuckDuckGo, Bing, etc.

Implements Model Context Protocol (MCP) server with pluggable search backends (SearXNG, Tavily, DuckDuckGo, Bing, Google, etc.) and exposes four tools—`one_search`, `one_scrape`, `one_map`, `one_extract`—for web search, scraping, and structured data extraction. Uses local browser automation via `agent-browser` for privacy-preserving searches and scraping without external API dependencies, with automatic Chromium detection across Chrome, Edge, and Canary installations. Integrates with Claude Desktop, Cursor, and Windsurf through standard MCP configuration files.

Scores updated daily from GitHub, PyPI, and npm data. How scores work