tavily-extract

Extract clean markdown or text from URLs via Tavily's extraction API.

1|Updated Mar 15, 2026

Search Tags:#markdown #api #oauth #text #extract #urls

Ready to run

npx skills add https://github.com/family3253/skill --skill tavily-extract-family3253

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: tavily-extract
Source: https://github.com/family3253/skill/tree/main/skills/tavily-extract
Command: npx skills add https://github.com/family3253/skill --skill tavily-extract-family3253

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires jq, curl, node, npx, mcp-remote, and includes scripts (resource) components.

What problem does it solve?

Tavily-extract eliminates the tedious manual work of pulling readable content from web pages by calling Tavily's extraction API to return clean markdown or text suitable for notes, summaries, or research pipelines.

Core Features & Use Cases

Extracts clean markdown or text from single or multiple URLs without writing code.
Supports focused extraction with a query term and per-source chunks to prioritize relevant content.
Works with either OAuth-based MCP tokens or API keys for secure authentication, enabling automation in research, content curation, and knowledge bases.

Quick Start

Run the extraction script with a JSON payload specifying the URLs to extract.

Frequently Asked Questions about tavily-extract

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I extract clean markdown from web URLs without writing code?▼

To extract clean markdown from multiple URLs, run the provided extraction script with a JSON payload specifying the URLs. This returns readable text or markdown content suitable for notes and research pipelines without requiring custom coding.

What is the best way to pull readable text from web pages for a research pipeline?▼

Using an extraction API like Tavily is an efficient way to pull readable text from web pages for research pipelines. It applies focused extraction with a query term and per-source chunks to prioritize relevant content across single or multiple URLs.

Do I need a Tavily account to extract content from URLs?▼

Yes, extracting content from URLs requires a Tavily account. You must authenticate securely using either a Tavily API key or an OAuth-based MCP token flow to access the extraction service.

Can I use curl to extract content from multiple URLs?▼

Yes, you can use curl to extract content from multiple URLs. The extraction service supports access via curl requests or the provided script, sending a JSON payload to retrieve clean markdown or text from the specified sources.

Does the Tavily extraction API support focused content queries?▼

Yes, the Tavily extraction API supports focused content queries. You can supply an optional query term and configure per-source chunks to prioritize and extract specific relevant content from the target URLs.

Why should I use an extraction API instead of manual web scraping for markdown?▼

An extraction API eliminates the tedious manual work of pulling readable content from web pages. It directly returns clean markdown or text suitable for summaries, bypassing the need to build and maintain custom scraping scripts.