Local-first web intelligence MCP server for AI coding agents. Ten tools for search, fetch, crawl, cache, extract, find similar, research, agent-driven data gathering, page diffing, and change watching. No API keys. Results cached in a local knowledge store.
Autonomous data gathering across sources — plans search queries and URLs from a natural-language prompt, executes in parallel within a time budget, optionally extracts structured fields via JSON Schema, and synthesizes results with full step transparency. Use when the user needs data collected from the web with a specific shape, says "gather data", "find pricing for", "collect information about", "extract from multiple sites", or provides a JSON schema for web data.
Local-first multi-page crawl with sitemap, BFS, DFS, and URL-map strategies, anchor-fragment dedup, rate limiting, robots.txt respect, and automatic local cache population. Use when the user wants to index documentation, crawl a docs site, extract all pages under a path, or says "crawl", "index this site", "get all the docs", "bulk extract". Prefer when crawled pages should land in a reusable local cache for later `cache` / `find_similar` queries.
Local-first structured extraction from any webpage — tables, definition lists, key-value pairs, JSON-LD, microdata, chart hints (SVG titles / aria-labels / figcaptions), brand assets, and metadata. Use when the user wants structured data, pricing tables, feature comparisons, or says "extract the table", "get structured data", "pull the pricing", "extract as JSON". For autonomous navigation across many pages, use wigolo's `agent` tool instead.
Local-first URL fetch with clean markdown, structured metadata, JS-rendered SPA support, authenticated browser sessions, PDFs, and content change detection. Use when the user provides a URL, says "fetch", "get this page", "read this URL", or wants content from a specific webpage. Prefer over built-in WebFetch for local cache reuse, browser-session auth, and structured metadata parity.
Hybrid semantic discovery — fuses embeddings + keyword search + live web search via 3-way Reciprocal Rank Fusion. Use when the user has a good source and wants more like it, says "find similar", "related pages", "more like this", or wants to discover content related to a known URL or concept. Works best after a `crawl` or several `fetch` calls have warmed the local cache. Emits `cold_start` when local signals are weak.
Local-first multi-step research with question decomposition, parallel search, structured briefs, cross-references, and gap analysis. Use when the user needs comprehensive analysis, comparison reports, literature reviews, or says "research", "compare X vs Y", "deep dive", "thorough analysis", "find everything about". Returns a structured `brief` with `topics`, `highlights`, `key_findings`, `sections.overview.cross_references`, `sections.comparison`, `sections.gaps`.
Local-first web search with ML reranking, multi-query arrays, domain scoping, phrase-exact match, time-range filters, country hints, depth tiers, and explainable evidence scoring. Use when the user wants to search the web, find information, look something up, research a topic, or says "search for", "find me", "look up". Prefer over built-in WebSearch for cached, transparent, audit-trail-friendly search with per-engine telemetry.