`search`

Pack: tavily · Endpoint: https://gateway.pipeworx.io/tavily/mcp

AI/LLM-optimized web search built for RAG: returns a synthesized natural-language answer plus a ranked list of sourced results (title, url, content snippet, relevance score). Prefer this over scraping a generic search engine when you need grounded, citable web context. Example: search({ query: “latest SpaceX Starship test result” })

Parameters

Name	Type	Required	Description
`query`	string	yes	The search query / question to research.
`search_depth`	string	no	Search depth: “basic” (fast, default) or “advanced” (deeper, more thorough).
`max_results`	number	no	Maximum number of results to return (default 5, max 20).
`topic`	string	no	Search topic: “general” (default) or “news” for recent news coverage.
`include_answer`	boolean	no	Whether to include a synthesized AI answer string (default true).
`_apiKey`	string	no	Optional — your own Tavily API key for higher limits; omit to use the shared Pipeworx key.

Example call

Arguments

{
  "query": "latest SpaceX Starship test result"
}

curl

curl -X POST https://gateway.pipeworx.io/tavily/mcp \
  -H 'Content-Type: application/json' \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"search","arguments":{"query":"latest SpaceX Starship test result"}}}'

TypeScript (@pipeworx/sdk)

import { Pipeworx } from '@pipeworx/sdk';
const pipeworx = new Pipeworx();

const result = await pipeworx.call('search', {
  "query": "latest SpaceX Starship test result"
});

More examples

{
  "query": "OpenAI GPT-5 release date",
  "search_depth": "advanced",
  "topic": "news",
  "max_results": 10,
  "include_answer": true
}

Response shape

Always returns: results

Field	Type	Description
`answer`	string \| null	Synthesized answer; may be empty when nothing matched
`results`	array
`response_time`	number \| null

Full JSON Schema

{
  "type": "object",
  "description": "Tavily web search. `answer` is a synthesized summary of the results.",
  "properties": {
    "answer": {
      "type": [
        "string",
        "null"
      ],
      "description": "Synthesized answer; may be empty when nothing matched"
    },
    "results": {
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "title": {
            "type": "string"
          },
          "url": {
            "type": "string"
          },
          "content": {
            "type": "string"
          },
          "score": {
            "type": [
              "number",
              "null"
            ]
          }
        },
        "required": [
          "title",
          "url"
        ]
      }
    },
    "response_time": {
      "type": [
        "number",
        "null"
      ]
    }
  },
  "required": [
    "results"
  ]
}

Connect

Add this to your MCP client config, or use one-click install buttons:

{
  "mcpServers": {
    "tavily": {
      "url": "https://gateway.pipeworx.io/tavily/mcp"
    }
  }
}

See Getting Started for client-specific install steps.

search