Refetch
Fetch pages, search the web, and extract structured data — built for AI agents.
От сообщества: Добавлен пользователем или импортирован; проверьте владельца перед подключениемРаботаетНужен API-ключГлобальныйБесплатноТолько чтение
Что умеет
- Check Usage: Check your current credit balance and API usage history. Free, does not cost a credit. Use this if you need to check how many credits remain or review usage patterns. Returns JSON: {"key"
- Fetch: Fetch any webpage and return its content as clean Markdown. This is the default tool for reading web pages. Use this whenever you need to read, summarize, extract information from, or analyze t
- Fetch Html: Fetch a URL and return raw unprocessed HTML. Only use this if you specifically need the HTML source, such as inspecting page structure, meta tags, or debugging rendering issues. In almost
Какие данные видит
Нужен ли аккаунт
Нужен API-ключ из настроек сервиса
Fetch pages, search the web, and extract structured data — built for AI agents.
Tools
- fetch — Any URL → clean markdown, optimized for LLM context windows
- fetch_html — Any URL → raw HTML with full SPA rendering
- fetch_structured_data — Extract JSON-LD schema.org data from any page
- search_web — Web search returning structured JSON results
- search_news — News search across 20+ countries with sources and dates
- check_usage — Check your credit balance and usage history (free)
Why refetch?
- One credit = one request, every endpoint, no multipliers
- $2.50 per 1,000 requests, credits never expire
- Block detection, CAPTCHA handling, and SPA rendering built in
- Streamable HTTP — no Docker, no stdio, no local process
500 free requests on signup, no credit card required. Get your API key →
Список инструментов сервера (6)
Технические названия из tools/list. Нужны только разработчикам.
| check_usage | Check your current credit balance and API usage history. Free, does not cost a credit. Use this if you need to check how many credits remain or review usage patterns. Returns JSON: {"key": "ftch_abc1...", "credits_remaining": 450, "usage": {"2025-01-15": {"/md": 30, "/s/web": 12}}} |
| fetch | Fetch any webpage and return its content as clean Markdown. This is the default tool for reading web pages. Use this whenever you need to read, summarize, extract information from, or analyze the content of a URL. The response is clean Markdown optimized for LLM context windows: scripts, ads, navigation, cookie banners, and other noise are stripped automatically. Returns the page content as Markdown text. News redirect URLs are automatically resolved to the real article URL. |
| fetch_html | Fetch a URL and return raw unprocessed HTML. Only use this if you specifically need the HTML source, such as inspecting page structure, meta tags, or debugging rendering issues. In almost all cases, use the "fetch" tool instead, which returns clean Markdown. Returns the full HTML source of the page as text. |
| fetch_structured_data | Extract structured data (JSON-LD) from a webpage. Use this when you need machine-readable schema.org data such as product details, recipes, events, articles, reviews, or organization info. Returns a JSON array of structured data objects found on the page. Returns an error if no structured data is present. |
| search_news | Search for recent news articles. Use this whenever you need current events, breaking news, or recent coverage of a topic. Returns articles with direct URLs to the original sources. Returns JSON: {"query": "...", "params": {"country": "US", "lang": "en"}, "count": 5, "articles": [{"title": "...", "url": "https://...", "source": {"name": "Reuters", "url": "https://..."}, "publishedAt": "2025-01-15T14:30:00Z"}]} Use "when" to control the lookback window: "1d" (past day), "7d" (past week), "30d" (past month), "180d" (past 6 months). |
| search_web | Search the web and return structured results. Use this whenever you need to find information, look something up, answer factual questions, or find URLs related to a topic. Returns JSON: {"query": "...", "params": {"country": "US", "lang": "en"}, "count": 10, "results": [{"title": "...", "url": "...", "snippet": "..."}]} Use the "country" parameter to get region-specific results (e.g. "SE" for Sweden, "DE" for Germany). The language is auto-selected from the country but can be overridden. |