search_on_engines
Search using only specified engines (e.g., arxiv, duckduckgo) with multi-page fanout and deduplication. Specify query and engines to get targeted results.
Instructions
Search using ONLY the specified engines (e.g. engines: ["arxiv", "duckduckgo"]).
Use when you have a specific source preference instead of the broad search tool.
NOTE: this instance's live engine/category list is currently unavailable — SearXNG was unreachable when the server started. Names you pass are forwarded and validated once SearXNG is reachable; restart the server after SearXNG is up to see the enabled list here.
Multi-page fanout (pages=N) and other knobs work the same as the broad search tool.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| pages | No | Multi-page fanout: fetch this many consecutive pages in parallel and merge with URL-based dedup. Default 1. Combines with pageno: pageno=3 + pages=2 fetches pages 3 and 4. Diminishing returns past page 2 (engines exhaust their result pools); going wide may also rate-limit upstream engines. Capped at 5 to bound token cost. | |
| query | Yes | Plain-language search query. Forwarded to each engine's native parser; engine-specific operators (e.g. site:, filetype:) are passed through unchanged. | |
| format | No | 'compact' (default) returns only url/title/content/engine for each result — typically much smaller, recommended for ranking and triage. 'full' adds: relevance score, publishedDate, the list of all engines that surfaced the result, and engine-specific metadata (authors, DOI, etc. for academic engines). Switch to 'full' only when you specifically need one of those fields. | |
| pageno | No | 1-indexed starting page number. Default 1. Higher pages fetch additional results from each engine, deduplicated against earlier pages by URL. Per-page yield drops sharply after the first 1-2 pages as engines exhaust their result pools. | |
| engines | Yes | Engine names to use, lowercase. Multiple engines run in parallel and results are merged. Must match this instance's enabled engines (the available list is enumerated in this tool's description above). | |
| language | No | Language filter, e.g. 'en', 'fr', 'de', 'pt-BR', or 'all' to disable filtering. If omitted, the SearXNG instance's configured default applies (NOT autodetected from the query, despite what the name suggests). | |
| time_range | No | Filter to results published within this time window. WARNING: not all engines implement time-range filtering — some (notably academic engines) return ZERO results when this is set instead of ignoring it. Set time_range only when freshness genuinely matters; if a query returns 0 results with time_range set, retry without it. | |
| safe_search | No | Safe-search level. 0 = off, 1 = moderate, 2 = strict. If omitted, the SearXNG instance's configured default applies (often 0 for self-hosted, but not guaranteed). |