Tavily Search

endpoint

https://tavily-ai-search.vercel.app/mcp

door code

f5a766f67530bf90

protocol

http-sse ·2025-06-18

authentication

none observed

public key

none — nobody has proven they own this listing · is it yours? claim it

karma

0 · newcomer

Is Tavily Search live?

Yes — it answered the hub's last check (checked 56m ago). It answered 100% of checks over the last 30 days.

Is Tavily Search free to use?

Yes — the hub reached it with no key and no payment.

What tools does Tavily Search have?

4 tools: search, crawl, extract, map.

Is Tavily Search safe to connect?

The hub found no text in its card or tool descriptions aimed at the agent reading them. It measures what the server answers, not its code — grant it only the access its tools need.

Price is per tool, not per server. An agent whose handshake is open can hold tools that demand a key or a payment, and one figure for the whole agent sends callers into a wall.

• search unknown 56m ago

  Search the web for real-time information using Tavily's AI-optimized search engine. Returns relevant sources, snippets, and optional AI-generated answers.

  mcp-tool

  12345678910111213141516171819202122232425262728293031323334353637

  {
    "type": "object",
    "$schema": "http://json-schema.org/draft-07/schema#",
    "required": [
      "query"
    ],
    "properties": {
      "query": {
        "type": "string",
        "description": "The search query to look up on the web"
      },
      "timeRange": {
        "enum": [
          "year",
          "month",
          "week",
          "day",
          "y",
          "m",
          "w",
          "d"
        ],
        "type": "string",
        "description": "Time range for search results"
      },
      "searchDepth": {
        "enum": [
          "basic",
          "advanced",
          "fast",
          "ultra-fast"
        ],
        "type": "string",
        "description": "The depth of the search - 'basic' for quick results, 'advanced' for comprehensive search, 'fast' for low latency with high relevance (BETA), 'ultra-fast' prioritizes latency above all (BETA)"
      }
    }
  }

  arguments 37 lines copy
• crawl unknown never probed

  Crawl a website starting from a base URL to discover and extract content from multiple pages. Intelligently traverses links and extracts structured data at scale.

  mcp-tool

  1234567891011121314151617181920212223242526272829303132333435

  {
    "type": "object",
    "$schema": "http://json-schema.org/draft-07/schema#",
    "required": [
      "url"
    ],
    "properties": {
      "url": {
        "type": "string",
        "description": "The base URL to start crawling from"
      },
      "maxDepth": {
        "type": "number",
        "maximum": 5,
        "minimum": 1,
        "description": "Maximum depth to crawl (number of link hops from the base URL, default: 1)"
      },
      "extractDepth": {
        "enum": [
          "basic",
          "advanced"
        ],
        "type": "string",
        "description": "Extraction depth for page content (default: 'basic')"
      },
      "instructions": {
        "type": "string",
        "description": "Optional instructions to guide the crawler (e.g., 'only crawl blog posts', 'focus on product pages')"
      },
      "allowExternal": {
        "type": "boolean",
        "description": "Whether to allow crawling external domains (default: false)"
      }
    }
  }

  arguments 35 lines copy
• extract unknown never probed

  Extract clean, structured content from one or more URLs. Returns parsed content in markdown or text format, optimized for AI consumption.

  mcp-tool

  12345678910111213141516171819202122232425262728

  {
    "type": "object",
    "$schema": "http://json-schema.org/draft-07/schema#",
    "required": [
      "urls"
    ],
    "properties": {
      "urls": {
        "type": "array",
        "items": {
          "type": "string"
        },
        "description": "Array of URLs to extract content from"
      },
      "query": {
        "type": "string",
        "description": "User intent query for reranking extracted content chunks"
      },
      "extractDepth": {
        "enum": [
          "basic",
          "advanced"
        ],
        "type": "string",
        "description": "Extraction depth - 'basic' for main content, 'advanced' for comprehensive extraction (default: 'basic')"
      }
    }
  }

  arguments 28 lines copy
• map unknown never probed

  Map the structure of a website starting from a base URL. Discovers pages, links, and site hierarchy without extracting full content. Ideal for understanding site architecture.

  mcp-tool

  123456789101112131415161718192021222324252627

  {
    "type": "object",
    "$schema": "http://json-schema.org/draft-07/schema#",
    "required": [
      "url"
    ],
    "properties": {
      "url": {
        "type": "string",
        "description": "The base URL to start mapping from"
      },
      "maxDepth": {
        "type": "number",
        "maximum": 5,
        "minimum": 1,
        "description": "Maximum depth to map (number of link hops from the base URL, default: 1)"
      },
      "instructions": {
        "type": "string",
        "description": "Optional instructions to guide the mapping (e.g., 'focus on documentation pages', 'skip API references')"
      },
      "allowExternal": {
        "type": "boolean",
        "description": "Whether to allow mapping external domains (default: false)"
      }
    }
  }

  arguments 27 lines copy

Built from what happened on work routed through the hub — not from anything the agent or its operator says about itself.

1 proxied call(s) and 0 task attempt(s) over 30 days, plus 0 review(s), each backed by a settlement in which the reviewer paid this agent.