Refetch

Fetch pages, search the web, and extract structured data — built for AI agents.

CommunityOnlineAPI key requiredGlobalFreeRead-only

What it can do

  • 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

What data it sees

Do you need an account

An API key from the service settings is required

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 →

How to connect

How to connect Refetch to Claude

The server address to paste into Claude settings:

https://refetch.run.tools

  1. Open Claude (claude.ai or the desktop app).
  2. Go to Settings → Connectors.
  3. Click Add custom connector.
  4. Paste the server address copied below into Remote MCP server URL and click Add.
  5. In a chat, click + → Connectors and switch the new connector on.

Custom connectors are available on Free, Pro, Max, Team and Enterprise plans (Free is limited to one). On Team and Enterprise an organization Owner adds the connector first under Organization settings → Connectors.

Authorization

After you click Add, a sign-in window for the service opens. Sign in with your own account and approve access. Claude never sees your password.

How to connect Refetch to ChatGPT

The server address to paste into ChatGPT settings:

https://refetch.run.tools

  1. Open ChatGPT in a browser (chatgpt.com). A Plus, Pro, Business, Enterprise or Edu plan is required.
  2. Turn on developer mode once: Settings → Apps → Advanced settings → Developer mode.
  3. Open Settings → Connectors and click Create.
  4. Fill in the form: Name (anything), Description (one line about what the service does), MCP server URL (copy it below).
  5. Under Authentication choose OAuth if the service requires sign-in, otherwise None. Click Create.
  6. In a new chat open + → Apps/Connectors and enable the connector.

OpenAI has renamed this section before (Connectors → Apps/Plugins). If the label differs, search settings for "developer mode". On Business/Enterprise workspaces an admin must allow custom connectors first.

Authorization

On first use ChatGPT opens the service's sign-in window. Sign in and approve access.

How to connect Refetch to Cursor

The server address to paste into Cursor settings:

https://refetch.run.tools

Fastest: click Open in Cursor below and confirm the prompt.

Manually:

  1. In Cursor open Settings → Cursor Settings → MCP and click Add new global MCP server.
  2. Paste the JSON copied below into ~/.cursor/mcp.json (per project: .cursor/mcp.json in the repo root).
  3. Save the file. The server appears in the MCP list; authorize it there if asked.

Authorization

If the service needs sign-in, an authorize button appears next to the server in the MCP list.

Server tool list (6)

Raw names from tools/list. Only developers need these.

check_usageCheck 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}}}
fetchFetch 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_htmlFetch 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_dataExtract 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_newsSearch 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_webSearch 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.