RamXX/mcp-tavily
mcp-tavily is hosted online, so all tools can be tested directly either in theInspector tabor in theOnline Client.
If you are the rightful owner of mcp-tavily and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.
Tavily MCP Server is a Model Context Protocol server that provides AI-powered web search capabilities using Tavily's search API.
Try mcp-tavily with chat:
Tools
Functions exposed to the LLM to take actions
tavily_web_search
Performs a comprehensive web search using Tavily's AI-powered search engine. Excels at extracting and summarizing relevant content from web pages, making it ideal for research, fact-finding, and gathering detailed information. Can run in either 'basic' mode for faster, simpler searches or 'advanced' mode for more thorough analysis. Basic is cheaper and good for most use cases. Supports filtering results by including or excluding specific domains. Use include_domains/exclude_domains parameters to filter by specific websites. Returns multiple search results with AI-extracted relevant content.
tavily_answer_search
Performs a web search using Tavily's AI search engine and generates a direct answer to the query, along with supporting search results. Best used for questions that need concrete answers backed by current web sources. Uses advanced search depth by default for comprehensive analysis.
Features powerful source control through domain filtering:
- For academic research: exclude_domains=["wikipedia.org"] for more scholarly sources
- For financial analysis: include_domains=["wsj.com", "bloomberg.com", "ft.com"]
- For technical documentation: include_domains=["docs.python.org", "developer.mozilla.org"]
- For scientific papers: include_domains=["nature.com", "sciencedirect.com"]
- Can combine includes and excludes to fine-tune your sources
Particularly effective for factual queries, technical questions, and queries requiring synthesis of multiple sources.
tavily_news_search
Searches recent news articles using Tavily's specialized news search functionality. Ideal for current events, recent developments, and trending topics. Can filter results by recency (number of days back to search) and by including or excluding specific news domains.
Powerful domain filtering for news sources:
- For mainstream news: include_domains=["reuters.com", "apnews.com", "bbc.com"]
- For financial news: include_domains=["bloomberg.com", "wsj.com", "ft.com"]
- For tech news: include_domains=["techcrunch.com", "theverge.com"]
- To exclude paywalled content: exclude_domains=["wsj.com", "ft.com"]
- To focus on specific regions: include_domains=["bbc.co.uk"] for UK news
Returns news articles with publication dates and relevant excerpts.
Prompts
Interactive templates invoked by user choice
tavily_web_search
Search the web using Tavily's AI-powered search engine
tavily_answer_search
Search the web and get an AI-generated answer with supporting evidence
tavily_news_search
Search recent news articles with Tavily's news search
Resources
Contextual data attached and managed by the client
