Search
Web, news, videos, images, code and people's voices, with time, language and site filters.
POST /v1/searchSearch the web, news, videos, images and code, hear what people say, and plug it all into your product or agent with one API.
Everything an assistant, an agent or an app needs to find fresh information and turn pages into clean data. Pay per call, start free.
Web, news, videos, images, code and people's voices, with time, language and site filters.
POST /v1/searchAny public page as clean Markdown, without menus, ads or cookie banners.
POST /v1/scrapeEvery URL of a site, or its pages as Markdown, depth and limits you choose.
POST /v1/map · /v1/crawlStructured JSON from a page: prices, specs, contacts, following your own schema.
POST /v1/extractA real browser that clicks, types, scrolls and waits, then returns the page.
POST /v1/interactWatch a page and know the moment its content changes.
POST /v1/monitorGive Claude, Cursor or any agent every tool above in one line of config.
POST /v1/mcpA private index per account and per end user: your documents, what your users open.
POST /v1/index · /v1/feedbackForums, open social networks and video sit beside the web. Ananke shows how many independent voices agree, so a copy-paste campaign does not pass for a consensus.
Many independent voices, from more than one kind of source.
A few independent voices.
Many posts, few independent voices: read with care.
One source so far.
One credit per search. Start with 500 free credits, no card.
Without a key you use the public sandbox (a few requests a day). With your key, calls spend your credits exactly like production.
Fill the form and run a request.
One REST API (and one MCP server) to search the open web by type, read any public page as Markdown or JSON, act in a real browser and watch pages for changes. Every endpoint takes and returns JSON over HTTPS.
| Base URL | Format | Auth |
|---|---|---|
__BASE__ | JSON, UTF-8 | Authorization: Bearer as_live_… |
1. Create a free account: you get 500 credits and your first API key. 2. Send a search. 3. Read results.
curl -X POST __BASE__/v1/search \
-H "Authorization: Bearer as_live_YOUR_KEY" \
-H "Content-Type: application/json" \
-d '{"query": "best e-bike battery for winter", "max_results": 5}'No key yet? Call the same endpoint without the header: the public sandbox answers a few requests per day so you can try it.
Send your secret key in the Authorization header as a Bearer token. Keys start with as_live_, are shown once when created and are stored hashed: we cannot show them again. Create, name and revoke keys in your dashboard. Never put a key in front-end code; call AnankeSearch from your server.
| Endpoint | Credits |
|---|---|
/v1/search (raw) | 1 |
/v1/search (mode answer) | 2 |
/v1/scrape, /v1/map, /v1/monitor | 1 |
/v1/crawl | 1 per page crawled |
/v1/extract, /v1/interact | 2 |
/v1/index (add a document) | 1 |
/v1/feedback, DELETE /v1/index | free |
Every response returns credits_used and remaining_credits. Rate limits: 60 requests per minute on the free plan, 300 on paid plans. Top-up credits never expire.
| Status | Meaning | What to do |
|---|---|---|
| 401 | Missing, malformed or revoked key | Check the header and the key |
| 402 | Not enough credits | Top up; detail.required says how many |
| 403 | The URL is not a public address | Only the public web can be fetched |
| 422 | Invalid parameters, or a page that could not be read | See detail |
| 429 | Rate or sandbox limit reached | Retry later, or use your own key |
Errors are JSON: {"detail": {"error": "…"}}.
Search by type with filters. Returns ranked results, a direct answer when there is one and, when the question deserves it, what people say.
| Parameter | Type | Default | Description |
|---|---|---|---|
query | string | required | What to search. Supports site:example.com and "exact phrases". |
type | string | web | web, news, videos, images, code or social. |
time_range | string | any | day, week, month, year. |
language | string | the query's | Result language: en, fr, es, pt, de… |
site | string | — | Only results from this site. |
max_results | integer | 5 | 1 to 20. |
mode | string | raw | answer adds an AI answer written from the results (2 credits). |
include_content | boolean | false | Adds each result's page as Markdown (content). |
social | string | auto | People's voices: auto, on, off. |
safe | boolean | true | Adult sites are left out unless the query plainly asks for them. false disables the filter. |
context | string | — | A few words about the conversation, to rank what fits it. |
user | string | — | Your end user's id: each gets a private index that learns. |
explain | boolean | false | Why each result ranks where it does. |
Each type returns only results of its kind. A video search returns videos (including video posts on social platforms), never encyclopedia pages padded in. When a plain query asks for a medium, for example elephant video or photos de Lomé, the type switches automatically and the response says so with "type_auto": true.
| type | Returns | Extra fields |
|---|---|---|
web | Pages | date |
news | Articles, freshest relevant first | source, published, thumbnail |
videos | Videos from video platforms and social networks | platform, thumbnail, duration, author, published, embed |
images | Images with their page | image, thumbnail, width, height, license, source |
code | Docs, Q&A, repositories | language, stars |
social | What people say: forums, open networks, public posts | platform, author |
curl -X POST __BASE__/v1/search -H "Authorization: Bearer as_live_YOUR_KEY" \
-H "Content-Type: application/json" \
-d '{"query": "elephant", "type": "videos", "max_results": 12}'Filters combine with every type. They are applied, not suggested: with time_range: "week" nothing older than a week comes back, even if it would rank well.
{
"query": "élections",
"type": "news",
"time_range": "week",
"language": "fr",
"site": "rfi.fr",
"max_results": 10
}{
"status": "success",
"query": "elephant video",
"type": "videos",
"type_auto": true,
"intent": "general",
"lang": "en",
"answer_direct": null,
"results_count": 2,
"results": [
{
"title": "…",
"url": "https://www.youtube.com/watch?v=…",
"snippet": "…",
"kind": "video",
"platform": "YouTube",
"thumbnail": "https://i.ytimg.com/vi/…/hqdefault.jpg",
"duration": "4:12",
"published": "2026-11-10",
"score": 0.812
}
],
"social": [],
"echo": [],
"credits_used": 1,
"remaining_credits": 499,
"latency_ms": 640
}| Field | Description |
|---|---|
results[] | Ranked results. Always title, url, snippet, kind, score; plus the type's extra fields. |
answer_direct | A short factual answer (a conversion, a definition) when one exists. |
answer | The AI answer, in mode answer. |
social[] | People's posts: platform, url, title, text, author, date. |
echo[] | Claims people make, with how many independent voices agree: corroborated, discussed, amplified, single. |
notice | Present when nothing of the requested type was found. |
explain[] | With explain: true: per result, the share of relevance, authority, source_quality, freshness and personal. |
"mode": "answer" writes a short answer from the results, with numbered citations, in the question's language (2 credits). "include_content": true adds the Markdown of each result page, ready for your own model (RAG).
{"query": "how long does a lithium battery last in the cold", "mode": "answer", "max_results": 6}For opinions, experiences, troubleshooting and news, AnankeSearch adds what people say on forums, open social networks and public posts, and groups their claims by how many independent voices agree. Duplicated posts from different accounts count as one voice. It measures agreement, not truth: treat amplified with care. Use "social": "on" to always include voices, "off" to skip them, or "type": "social" to get voices only.
Each account, and each end user you name with user, has a private index that nobody else can see.
| Call | What it does |
|---|---|
POST /v1/feedback | {"url", "query", "user"}: your user opened this result. Similar searches lift it. Free. |
POST /v1/index | {"url", "title", "text", "user"}: add your own page (help center, product sheet). It appears beside web results when it matches. 1 credit. |
DELETE /v1/index | {"user"} (optional): erase everything learned for the account or one user. |
A public page as clean Markdown. Parameters: url (required), max_chars (500–50 000, default 15 000). Returns title, content.
{"url": "https://example.com/article", "max_chars": 15000}Every internal URL of a site. Parameters: url, limit (1–500, default 100). Returns domain, total_links, links[].
The pages of a site as Markdown. Parameters: url, limit (1–25 pages, default 5), max_depth (1–4, default 2). Returns base_url, pages_crawled, data[] with url, title, content. 1 credit per page.
Structured JSON from a page. Parameters: url, prompt (what to extract), optional schema (a JSON schema the output must follow). Returns data.
{
"url": "https://shop.example/product/42",
"prompt": "Product name, price with currency, and whether it is in stock",
"schema": {"type": "object", "properties": {"name": {"type": "string"}, "price": {"type": "string"}, "in_stock": {"type": "boolean"}}}
}Runs actions in a real browser, then returns the page as Markdown. Parameters: url, actions[], wait_ms (0–5000), max_chars. Actions: {"type": "click", "selector"}, {"type": "type", "selector", "text"}, {"type": "scroll", "direction": "down"}, {"type": "wait", "seconds"}.
{
"url": "https://example.com/search",
"actions": [
{"type": "type", "selector": "input[name=q]", "text": "solar panels"},
{"type": "click", "selector": "button[type=submit]"},
{"type": "wait", "seconds": 1.5}
],
"wait_ms": 1000
}Checks a page against its last known version. Parameter: url. Returns has_changed, change_count, last_checked. Call it on a schedule to watch prices, policies or job posts.
AnankeSearch speaks the Model Context Protocol (JSON-RPC over HTTP) at /v1/mcp. Add it to Claude Desktop, Cursor or any MCP client; calls spend credits like the REST API.
{
"mcpServers": {
"anankesearch": {
"url": "__BASE__/v1/mcp",
"headers": {"Authorization": "Bearer as_live_YOUR_KEY"}
}
}
}| Tool | Does |
|---|---|
anankesearch_web_search | Search with type, time_range, language, site, mode |
anankesearch_scrape_url | Page → Markdown |
anankesearch_map_domain | All URLs of a site |
anankesearch_crawl_site | Site pages → Markdown |
anankesearch_extract_data | Page → JSON |
anankesearch_interact_page | Browser actions |
anankesearch_monitor_page | Change detection |
curl -X POST __BASE__/v1/mcp -H "Authorization: Bearer as_live_YOUR_KEY" \
-H "Content-Type: application/json" \
-d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"anankesearch_web_search","arguments":{"query":"elephant","type":"videos"}}}'Search with include_content: true, pass the Markdown of the top results to your model, cite the URLs.
type: "news", time_range: "day", language set to your user's. Deduplicate by url between runs.
type: "videos" and show thumbnail, duration and platform; open url or play embed when present.
type: "images" and keep results whose license fits your use; always link back to url.
Add your help pages with POST /v1/index; they come first for matching questions, beside the web.
/v1/extract the fields you need, and /v1/monitor the page every hour; re-extract when has_changed.
social: "on" and read echo: claims marked corroborated come from several independent voices.
One credit per search, 500 free credits to start. Monthly plans, or top-ups that never expire.
| Every plan includes | |
|---|---|
| All search types and filters | web, news, videos, images, code, voices |
| Scrape, map, crawl, extract, interact, monitor | same credits on every plan |
| MCP server | for Claude, Cursor and any agent |
| Private index per account and per end user | never shared |
curl -X POST __BASE__/v1/search \
-H "Authorization: Bearer as_live_YOUR_KEY" \
-H "Content-Type: application/json" \
-d '{"query": "elephant", "type": "videos"}'| Time | Endpoint | Query | Mode | Latency | Credits |
|---|---|---|---|---|---|
| No requests yet. | |||||