mcpField
T
tavily-search

tavily-search

github.com/tavily-aiProductivity49136.4k installsUpdated 8w ago
Repository

About tavily-search

A Tavily search skill for users seeking web information. It uses the tvly CLI to return web results with content snippets and relevance scores suited to LLM workflows.

Key features

  1. 01Search the web by query
  2. 02Filter by date, topic, and country
  3. 03Retrieve raw page content
  4. 04Return structured JSON results

Use cases

  1. 01Find web sources on a specific topic
  2. 02Filter recent news or information by date
  3. 03Limit results to trusted domains to verify facts

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/tavily-ai/skills --skill tavily-search

After installing, type/tavily-searchin Claude Code to confirm it loaded.

Details

From the project README

tavily search

Web search returning LLM-optimized results with content snippets and relevance scores.

Before running

Run search directly when tvly is available. Search supports capped keyless access, so do not look for an API key or authenticate before the first request.

If tvly is missing, follow the tavily-cli setup before retrying. If the keyless cap is reached in an interactive session, run tvly login to open browser OAuth, then retry the original search once. In an unattended environment, report the cap and authentication options instead of starting an interactive flow. Do not start a second login immediately after guided setup has completed.

When to use

  • You need to find information on any topic
  • You don't have a specific URL yet
  • First step in the workflow: search → extract → map → crawl → research

Quick start

# Basic search
tvly search "your query" --json

# Advanced search with more results
tvly search "quantum computing" --depth advanced --max-results 10 --json

# Recent news
tvly search "AI news" --time-range week --topic news --json

# Domain-filtered
tvly search "SEC filings" --include-domains sec.gov,reuters.com --json

# Include full page content in results
tvly search "react hooks tutorial" --include-raw-content --max-results 3 --json

Options

OptionDescription
--depthultra-fast, fast, basic (default), advanced
--max-resultsMax results, 0-20 (default: 5)
--topicgeneral (default), news, finance
--time-rangeday, week, month, year
--start-dateResults after date (YYYY-MM-DD)
--end-dateResults before date (YYYY-MM-DD)
--include-domainsComma-separated domains to include
--exclude-domainsComma-separated domains to exclude
--countryBoost results from country
--include-answerInclude AI answer (basic or advanced)
--include-raw-contentInclude full page content (markdown or text)
--include-imagesInclude image results
--include-image-descriptionsInclude AI image descriptions
--chunks-per-sourceChunks per source (advanced/fast depth only)
-o, --outputSave the JSON response to a file
--jsonStructured JSON output

Search depth

DepthSpeedRelevanceBest for
ultra-fastFastestLowerReal-time chat, autocomplete
fastFastGoodNeed chunks, latency matters
basicMediumHighGeneral-purpose (default)
advancedSlowerHighestPrecision, specific facts

Tips

  • Keep queries under 400 characters — think search query, not prompt.
  • Break complex queries into sub-queries for better results.
  • Use --include-raw-content when you need full page text (saves a separate extract call).
  • Use --include-domains to focus on trusted sources.
  • Use --time-range for recent information.
  • Verify identity-sensitive facts at the exact primary source. For releases, versions, ownership, or similarly named projects, confirm the official repository or domain instead of trusting a generated answer or package-name match alone.
  • Read from stdin: echo "query" | tvly search - --json

See also

Comments

Markdown supported