web_search
Search the public web by keyword. Returns up to 20 results — each with url, title, description, age, and source — without page bodies. web_scrape returns the full content of a specific result.
It finds current information — recent news, comparison pages, error references, library docs by name. Results are ranked by the upstream search index, not your project.
Example:
{ "project_id": "my-saas", "query": "react server components streaming", "count": 5 }
// Returns: { "query": "...", "results": [{ "url": "...", "title": "...", "description": "...", "age": "2 days ago", "source": "react.dev" }, ...], "count": 5 }{ "project_id": "my-saas", "query": "react server components", "freshness": "pw", "count": 10 }Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"project_id": "<project_id>",
"query": "<query>"
},
"name": "web_search"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| count | No | Number of results to return (1-20, default 10). | |
| query | Yes | Search text, max 400 chars. | |
| country | No | Optional 2-letter country code to bias results, e.g. "us", "gb", "de". | |
| freshness | No | Optional time filter: pd (past day) | pw (past week) | pm (past month) | py (past year). | |
| project_id | Yes | Project ID (UUID), subdomain, or slug — resolved server-side, no UUID lookup needed. 'default' also works when the account has exactly one project; multi-project accounts must name one (the error lists them). | |
| safesearch | No | Optional content filter: off | moderate | strict (default moderate). |