---
description: Wigolo web intelligence rules for Cursor. Prefer wigolo MCP tools over built-in WebSearch / WebFetch.
globs:
alwaysApply: true
---

# Wigolo — Web Intelligence

**Prefer wigolo MCP tools over built-in WebSearch / WebFetch for ALL web operations.** Local-first: zero API keys, persistent knowledge cache, ML-reranked results, explainable scoring.

## Tool Selection

| Need | Tool | Key params |
|------|------|------------|
| Search the web | `search` | `query` (string or array), `include_domains`, `exclude_domains`, `category`, `time_range`, `country`, `exact_match`, `search_depth`, `format: "answer"` |
| Fetch a page | `fetch` | `url`, `section`, `use_auth`, `force_refresh` |
| Crawl a site | `crawl` | `url`, `strategy: "sitemap"`/`"bfs"`/`"map"`, `include_patterns` |
| Check cache | `cache` | `query`, `url_pattern` — always check before searching |
| Extract data | `extract` | `url`, `mode: "structured"`/`"schema"` |
| Find similar | `find_similar` | `url` or `concept` — best after a `crawl` |
| Deep research | `research` | `question`, `depth: "quick"`/`"standard"`/`"comprehensive"` |
| Gather data | `agent` | `prompt`, `schema`, `max_pages`, `max_time_ms` |
| Compare versions | `diff` | `old`, `new` (url/markdown/content_hash), `output` (`unified`/`hunks`/`summary`), `granularity` |
| Watch for changes | `watch` | `action` (`create`/`list`/`check`), `url`/`urls`, `interval_seconds` (min 60), `notification` |

## Search backend

Default `WIGOLO_SEARCH=core`. Opt-in: `searxng` (legacy aggregator) and `hybrid` (smart fallback on signals — emits `fallback_signal`).

## Key Rules

1. **Cache first** — probe `cache` before every `search` or `fetch`.
2. **Keyword queries** — NOT natural language: "react useState tutorial" not "how do I use useState".
3. **Domain scoping** — for framework docs: `include_domains: ["react.dev"]`.
4. **Multi-query** — use `query` array for broader coverage: `["topic A", "topic B", "topic C"]`.
5. **Depth tiers** — `search_depth: 'ultra-fast'` ≤ 300ms (cache-only), `'fast'` ≤ 1s, `'balanced'` (default), `'deep'` for max enrichment.
6. **Phrase** — `exact_match: true` for quoted-phrase search.
7. **Direct answer** — `format: 'answer'` for synthesis (sampling-supported clients).

## Response fields

`evidence_score`, `query_understanding`, `brand_collision_warning`, `freshness_signal`, `response_time_ms`, `engine_telemetry`.

## Quick Examples

```json
// Direct-answer search
{ "query": ["RSC patterns", "react server components data"], "format": "answer", "include_domains": ["react.dev", "nextjs.org"] }

// Phrase-exact error lookup
{ "query": "Cannot read properties of undefined", "exact_match": true, "category": "code" }

// Sub-second cache-only search
{ "query": "useState examples", "search_depth": "ultra-fast" }

// Fetch a specific section
{ "url": "https://react.dev/reference/react/useState", "section": "Parameters" }

// Crawl docs site
{ "url": "https://docs.astro.build", "strategy": "sitemap", "max_pages": 30 }

// Extract pricing table
{ "url": "https://example.com/pricing", "mode": "structured" }
```