{
  "name": "io.github.tavily-ai/tavily-mcp",
  "description": "Tavily is a search API purpose-built for AI agents — every result is pre-cleaned, summarised, and shipped with source citations. The Tavily MCP exposes web search, news search, and a single-call \"search and extract\" path that returns Markdown bodies alongside the ranked list. Strong default for research-heavy agent workflows.",
  "status": "active",
  "version": "latest",
  "_meta": {
    "com.top-mcps/lastVerified": "2026-05-06",
    "com.top-mcps/score": {
      "value": 90,
      "rubricVersion": "2026-04",
      "lastComputed": "2026-05-11T09:29:11.919Z",
      "methodology": "https://top-mcps.com/about/methodology"
    },
    "com.top-mcps/stats": {
      "fetchedAt": "2026-05-11T09:29:10.957Z",
      "githubStars": 1944,
      "lastCommitAt": "2026-05-09T00:34:38Z",
      "npmWeeklyDownloads": 30105
    }
  },
  "repository": {
    "url": "https://github.com/tavily-ai/tavily-mcp",
    "source": "github"
  },
  "author": {
    "name": "Tavily"
  },
  "packages": [
    {
      "registryType": "npm",
      "registryBaseUrl": "https://registry.npmjs.org",
      "identifier": "tavily-mcp",
      "version": "latest",
      "transport": {
        "type": "stdio"
      },
      "environmentVariables": [
        {
          "name": "TAVILY_API_KEY",
          "description": "TAVILY_API_KEY — required credential for Tavily.",
          "isRequired": true,
          "isSecret": true
        }
      ]
    }
  ],
  "capabilities": {
    "tools": [
      {
        "name": "tavily-search",
        "description": "Run a web search and return ranked results with snippets.",
        "sideEffect": "network",
        "args": [
          {
            "name": "query",
            "type": "string",
            "required": true
          },
          {
            "name": "topic",
            "type": "string",
            "required": false
          },
          {
            "name": "max_results",
            "type": "number",
            "required": false
          }
        ]
      },
      {
        "name": "tavily-extract",
        "description": "Fetch and clean the body of one or more URLs.",
        "sideEffect": "network",
        "args": [
          {
            "name": "urls",
            "type": "string[]",
            "required": true
          }
        ]
      },
      {
        "name": "tavily-news",
        "description": "Search news sources only, with publication-date metadata.",
        "sideEffect": "network",
        "args": [
          {
            "name": "query",
            "type": "string",
            "required": true
          },
          {
            "name": "days",
            "type": "number",
            "required": false
          }
        ]
      }
    ],
    "security": {
      "scope": "network",
      "sandbox": "Calls the Tavily API over HTTPS with the key in TAVILY_API_KEY. The MCP itself only reads from Tavily — no write capability, no local filesystem reach. Rate limits and per-call cost are the main operational concerns.",
      "gotchas": [
        "Per-call cost rises with `include_raw_content: true` — set a budget at the API-key level before unleashing an autonomous loop.",
        "Tavily caches some searches; if you need real-time freshness for time-sensitive prompts, pass `include_raw_content: true` or pair with Brave Search for news-burst coverage."
      ]
    }
  },
  "_links": {
    "html": "https://top-mcps.com/mcp/tavily",
    "markdown": "https://top-mcps.com/mcp/tavily.md",
    "methodology": "https://top-mcps.com/about/methodology"
  }
}