search

Active

Tool of Exa

declared in 0.1.0

Neural/semantic web search — find pages by meaning, not just keywords. Returns title, URL, published date, author, and relevance score. Optionally retrieve clean page text inline. Example: search({ query: "startups building AI agents for customer support", num_results: 10, type: "neural" })

Parameters schema

{
  "type": "object",
  "required": [
    "query"
  ],
  "properties": {
    "type": {
      "type": "string",
      "description": "Search mode: 'neural' (semantic/meaning-based), 'keyword' (traditional), or 'auto' (Exa picks). Default 'auto'."
    },
    "query": {
      "type": "string",
      "description": "The search query — describe what you want by meaning, e.g. \"recent research on protein folding with diffusion models\""
    },
    "_apiKey": {
      "type": "string",
      "description": "Optional — your own Exa API key for higher limits; omit to use the shared Pipeworx key."
    },
    "category": {
      "type": "string",
      "description": "Optional focus category, e.g. 'company', 'research paper', 'news', 'pdf', 'github', 'tweet'."
    },
    "num_results": {
      "type": "number",
      "description": "Number of results to return (default 10, max 25)"
    },
    "include_text": {
      "type": "boolean",
      "description": "If true, include the clean parsed page text (up to 2000 chars) for each result. Default false."
    }
  }
}

What this tool wraps· 0 endpoints

min confidence0.70 0.50

No endpoints wrapped at confidence ≥ 0.70.

Parent server

Exa

https://github.com/pipeworx-io/mcp-exa

1/7 registries

View full server →