"tavily" matching MCP servers:

Enables AI agents to perform real-time web searches and extract clean, LLM-readable content from URLs using the Tavily API.

A typed FastMCP server that wraps Tavily's web research API, providing tools for search, extract, map, crawl, and research workflows via MCP with prompts and resources.

A Model Context Protocol server for web scraping and searching, with automatic fallback from Tavily to Firecrawl for fetching web content.

Pools multiple Tavily API keys into a single local MCP server with round-robin rotation and automatic failover, exposing Tavily search, extract, crawl, map, and research tools to AI agents via stdio.

Provides advanced web search, content extraction, site crawling, mapping, and AI-powered research capabilities through the Tavily API with automatic multi-key fallback for rate limiting.

MCP server for web page fetching (converting to Markdown/text with automatic fallback between Tavily and Firecrawl) and web search via Tavily.

Enables MCP clients to perform Tavily-compatible search and extract operations against a self-hosted TrailSearch/open-tavily API by using a custom base URL instead of the default Tavily endpoint.

MCP server that provides web search capabilities using the Tavily API.

MCP server using Tavily API for web search, enabling web search queries via stdio transport.

MCP server that enables web search via Tavily API and chess player stats via Chess.com API.

Enables web search via Tavily API and URL shortening with custom aliases and fallback services.

Enables web search via Tavily API, dice rolling, and marketing/company news retrieval through MCP tools.

Web search MCP server using Tavily API, enabling natural language queries to search the web.

Web search for AI agents across 6 engines (Serper, Brave, Exa, Tavily, Firecrawl, Perplexity) through one search tool. Routes each query to the cheapest engine that clears a quality bar and caches repeats. Hosted, streamable-HTTP, BYOK supported.

MCP server for creating day-by-day trip itineraries in SQLite, with a planner agent that uses a Tavily search scout via tool boundaries. Enforces guard rails like rejecting activities on out-of-range days.

A dual-path web search MCP server for Claude Code that cross-validates results via Tavily/Firecrawl and Google, explicitly returning sources to reduce hallucinations.

A Grok-first multi-source search MCP for AI agents that integrates Grok, Tavily, AnySearch, and Firecrawl to provide unified search results, cross-verification, and web content fetching.

A deep-research MCP server exposing a single task-augmented tool that runs GPT-Researcher with Tavily search, Anthropic Claude, and OpenAI embeddings, streaming progress via MCP tasks and Upjack entity stream.

Enables agents to search the main academic literature APIs (arXiv, Crossref, Semantic Scholar) and the web via Tavily, and to extract full text from PDFs or web pages, returning each source's own native metadata fields.

An MCP server that turns CI failures, pull requests, security alerts, and Slack threads into Linear issues, Slack posts, changelogs, docs, and reports with evidence attached, through 25 agent-run workflows over 59 tools spanning GitHub, Linear, Slack, Notion, Google Docs, Google Calendar, Google Sheets, Firecrawl, and Tavily. It also handles credential setup in the OS keychain and pauses for approval before any create, send, change, or delete call.