One index. Reach it over MCP or plain HTTP.

All routes are served from the API host. Responses are JSON. Requests with a body are application/json.

https://api.ipnops.ai

A Streamable-HTTP, stateless MCP server at POST /mcp. Add one connector and six tools appear inside your runtime: ipnops_search, ipnops_answer, ipnops_extract, ipnops_research, ipnops_research_status, and ipnops_monitor. Each ships an outputSchema, so tool results arrive as typed structure — not text to re-parse.

# one connector — Ipnops becomes an agent tool
{ "ipnops": {
    "transport": "http",
    "url": "https://api.ipnops.ai/mcp"
  } }

{ "tools": [
  { "name": "ipnops_search", "outputSchema": {…} },
  { "name": "ipnops_answer", "outputSchema": {…} },
  …extract, research, research_status, monitor
] }

A tools/call to answer returns the same AnswerResult shape documented under /answer as structuredContent.

Hybrid retrieve over the live-web index: a lexical arm and a dense semantic arm, fused and reranked. Returns typed highlights, each self-citing its source passage.

curl -sS https://api.ipnops.ai/search \
  -H "content-type: application/json" \
  -d '{ "query": "sqlite file format" }'

{ "highlights": [{ 
    "text": "…passage…", "score": 0.91,
    "source": { "url": "…" } }],
  "arms": { "lexical": true, "dense": true, "reranked": true } }

Consolidates highlights into one grounded answer with Ipnops' own tiered reasoner. The response is the agent-native shape: marker-per-claim citations, a claims array with per-claim verdicts and evidence quotes, one calibrated confidence scalar, and a sufficiency verdict that says whether the evidence actually covered the question.

curl -sS https://api.ipnops.ai/answer \
  -H "content-type: application/json" \
  -d '{ "query": "who maintains sqlite?" }'

{ "answer": "… [1] … [2]",
  "citations": [{ "marker": 1, "url": "…", "text": "…" }],
  "claims": [{ "text": "…", "verdict": "supported",
    "quotes": ["…"], "grounded": true }],
  "confidence": 0.84, "sufficiency": "supported",
  "conflicts": [], "grounding": "own-index", "tier": "floor" }

grounding is one of own-index, web, places, or none — the reach ladder falls through in that order and never fabricates when it misses. sufficiency is supported, conflicting (sources disagree — see conflicts), or insufficient (treat the answer as an abstain).

Deep research as a durable run. Returns a run_id immediately (202); the engine then iterates — answer, find the claims it couldn't ground, crawl the gap, re-answer — checkpointing every step. The run survives restarts, and pages crawled along the way stay in the index.

curl -sS https://api.ipnops.ai/research \
  -H "content-type: application/json" \
  -d '{ "query": "…" }'

# 202 ◂
{ "run_id": "run_5c1f…", "status": "queued" }

# poll
GET /research/:id

# stream — SSE, resumes from Last-Event-ID
GET /research/:id/events
# events: started → iteration → gap → crawl → completed

# cooperative cancel
POST /research/:id/cancel

The terminal result is the same AnswerResult shape as /answer, plus iterations and pagesIndexed.

Watch a question instead of asking it once. Each sweep re-answers the query and diffs the grounded claim set against the last snapshot — a deterministic normalized-text comparison, zero extra model calls. The webhook fires only when the facts change: rephrasing is silence, a new number is a signal.

POST /monitor      # register → 201 { monitor_id }
GET /monitor       # list
GET /monitor/:id   # one monitor + last snapshot
DELETE /monitor/:id
POST /monitor/run   # the cron target — sweep + diff

{ "monitor_id": "mon_9b2e…",
  "diff": { "addedClaims": ["…"], "removedClaims": ["…"],
           "confidenceDelta": -0.05 },
  "answer": "… [1]", "citations": […], "confidence": 0.81
}

Grow the index. Pass exactly one of seed (crawl one domain) or query (fan a free-text query across the discovery ladder and crawl what it finds).

curl -sS https://api.ipnops.ai/index/seed \
  -H "content-type: application/json" \
  -d '{ "query": "sqlite documentation", "maxSeeds": 5 }'

Generative Engine Optimization (GEO) makes your real site retrievable by AI answer engines — the systems that now write a user's first impression of you and cite a handful of sources instead of listing a page of links. Ipnops observes which AI crawlers actually hit you, audits the on-page signals that decide retrieval, and scores you per engine across the Western and Chinese frontier. It enriches the page you already ship — no cloaking, no mirror page served only to bots.

The tag vs. the server SDK

The client tag is a one-line script that reports your live on-page signals (structured data present, server-render state, meta) from a real browser. The server SDK reads your request logs and tags real AI-crawler hits. Both are required, and the server SDK is not optional: AI crawlers do not run JavaScript, so the client tag never sees them. The only place a crawler's visit shows up is server-side, in the request log. That log truth — who came, to which paths, and what HTML they got — is the differentiator on-page audits alone can't match.

<!-- reports live on-page signals -->
<script async
  src="https://api.ipnops.ai/geo/tag.js"
  data-site="example.com"></script>

// crawlers don't run JS — the server sees them
import { ipnops } from "@ipnops/geo";

app.use(ipnops({ site: "example.com" }));
// tags every AI-crawler request in your logs

Install on any framework or hosted builder

The tag drops into any HTML head. For React and Next, install it declaratively; on the server, add the SDK middleware where requests land. On a hosted builder, paste the tag into the head-code field it already gives you — no code required.

Audit signals

The on-page audit grades the four levers that decide whether an engine can retrieve and cite you — each scored per page, per engine.

The nine engines

Ipnops scores five Western engines — ChatGPT, Perplexity, Google AI, Copilot, Claude — and four Chinese frontier engines most tools ignore: Qwen, GLM, Kimi, and DeepSeek. Each is matched by its published crawler user-agent where one exists.

The DeepSeek nuance — DeepSeek publishes no crawler user-agent and fetches browser-like, so it is effectively unobservable in logs; there is no hit to report. The lever that reaches it is retrieval readiness on your real page — serverRender plus structuredData. Ipnops covers DeepSeek through that readiness score, not through crawler observation, and labels it as such rather than faking a hit.

Structured data is the lever

In-page schema.org JSON-LD resolves your entities — org, product, FAQ, author — into a graph the model can bind to instead of guessing from prose. It is the highest-leverage GEO move and the one Ipnops grades first. It lives on the page you already serve.

<script type="application/ld+json">
{ "@context": "https://schema.org",
  "@type": "Organization", "name": "Acme",
  "url": "https://example.com",
  "description": "Acme grades AI-answer retrieval."
}
</script>