search
Pack: exa · Endpoint: https://gateway.pipeworx.io/exa/mcp
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
| Name | Type | Required | Description |
|---|---|---|---|
query | string | yes | The search query — describe what you want by meaning, e.g. “recent research on protein folding with diffusion models” |
num_results | number | no | Number of results to return (default 10, max 25) |
type | string | no | Search mode: ‘neural’ (semantic/meaning-based), ‘keyword’ (traditional), or ‘auto’ (Exa picks). Default ‘auto’. |
include_text | boolean | no | If true, include the clean parsed page text (up to 2000 chars) for each result. Default false. |
category | string | no | Optional focus category, e.g. ‘company’, ‘research paper’, ‘news’, ‘pdf’, ‘github’, ‘tweet’. |
_apiKey | string | no | Optional — your own Exa API key for higher limits; omit to use the shared Pipeworx key. |
Example call
curl -X POST https://gateway.pipeworx.io/exa/mcp \
-H 'Content-Type: application/json' \
-d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"search","arguments":{}}}'Connect
Add this to your MCP client config, or use one-click install buttons:
{
"mcpServers": {
"exa": {
"url": "https://gateway.pipeworx.io/exa/mcp"
}
}
}See Getting Started for client-specific install steps.