engines
Read-onlyIdempotent
Lists all valid search engine names for the engines= parameter, enabling discovery of installable engines before use.
Instructions
List engine names accepted by the engines= parameter of search / research.
Best for:
- Discovering what's installable before passing a non-default engine.
- Building user-facing UIs that let humans pick engines.
Not recommended for:
- Calling on every search — the list is static; cache it.
Returns:
- The live, complete list of engine name strings. The buckets below are
illustrative; always trust the returned list over this doc.
Common mistakes:
- Passing one of these names as a query to `search` — they go in the
`engines=` argument, not `query`.
- Passing a key-only engine (brave_api/serper/tavily/google_cse) with no key
configured — it returns an actionable error, not results.
Defaults: duckduckgo + mojeek + googlenews + bing (reliable, all-HTTP,
low-latency; googlenews is an RSS index with structured publish
dates and its URLs resolve to the real publisher on
fetch/research; bing's www4 edge answers in ~0.3s).
Keyless opt-in: google + serpsearch (Google SERP scrapers, HTTP-first),
anysearch (JSON aggregator), startpage (browser-rendered, slower),
brave (PoW captcha after a few calls), baidu
(CN index), bilibili (CN video), zhihu (CN Q&A, often login-gated),
searx (public-instance meta-search; set SEARCH_MCP_SEARX_INSTANCES
if it returns nothing).
Key-required (configure via admin UI / SEARCH_MCP_*_API_KEY): brave_api,
serper, tavily, google_cse.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Output Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |