Refetch
Fetch pages, search the web, and extract structured data — built for AI agents.
Quick Start
# Connect this server (installs CLI if needed)
npx -y smithery mcp add refetch/web
# Browse available tools
npx -y smithery tool list refetch/web
# Get full schema for a tool
npx -y smithery tool get refetch/web check_usage
# Call a tool
npx -y smithery tool call refetch/web check_usage '{}'Direct MCP Connection
Endpoint: https://refetch.run.tools
Required config:
X-API-Key(header) — Your refetch.cloud API key (starts with ftch_). Get one free at https://refetch.cloud
Tools (6)
check_usage— Check your current credit balance and API usage history. Free, does not cost a credit. Use this if you need to check ho…fetch— Fetch any webpage and return its content as clean Markdown. This is the default tool for reading web pages.fetch_html— Fetch a URL and return raw unprocessed HTML. Only use this if you specifically need the HTML source, such as inspecting…fetch_structured_data— Extract structured data (JSON-LD) from a webpage. Use this when you need machine-readable schema.org data such as produ…search_news— Search for recent news articles. Use this whenever you need current events, breaking news, or recent coverage of a topi…search_web— Search the web and return structured results. Use this whenever you need to find information, look something up, answer…
# Get full input/output schema for a tool
npx -y smithery tool get refetch/web Prompts (3)
latest_news(topic) — Find and summarize the latest news coverage on a topic.research_topic(topic) — Search the web for a topic and compile findings into a structured overview.summarize_page(url) — Fetch a URL and produce a concise summary of its content.