MCP ConfigsApr 7, 2026·2 min read

Jina Reader — AI-Friendly Web Content Extraction

Convert any URL to clean markdown for AI consumption. Free API at r.jina.ai strips ads, navigation, and clutter. Used by AI agents for web research and RAG.

MC
MCP Hub · Community
Quick Use

Use it first, then decide how deep to go

This block should tell both the user and the agent what to copy, install, and apply first.

# Prefix any URL with r.jina.ai
curl https://r.jina.ai/https://example.com

# Or use the API
curl -H "Accept: text/markdown" https://r.jina.ai/https://github.com/jina-ai/reader

Returns clean markdown — no ads, no navigation, no clutter.

What is Jina Reader?

Jina Reader is a free API that converts any web page into clean, AI-friendly markdown. Simply prefix a URL with r.jina.ai/ and get back structured content stripped of ads, navigation, scripts, and visual clutter — perfect for feeding into LLMs, RAG pipelines, and AI agents.

Answer-Ready: Jina Reader is a free API that converts any URL to clean markdown for AI consumption. Prefix any URL with r.jina.ai/ to strip ads, navigation, and clutter. Used by AI agents and RAG pipelines for web research. 20k+ GitHub stars.

Best for: AI agent developers who need web content extraction. Works with: Any HTTP client, LangChain, LlamaIndex, Claude Code. Setup time: Zero — just use the URL prefix.

Core Features

1. URL-to-Markdown

import requests

url = "https://r.jina.ai/https://docs.anthropic.com/en/docs/agents"
response = requests.get(url, headers={"Accept": "text/markdown"})
markdown = response.text
# Clean markdown ready for LLM consumption

2. Search Integration

# Search the web and get markdown results
curl https://s.jina.ai/best+AI+coding+tools+2026

Returns search results as structured markdown with titles, URLs, and content snippets.

3. Options

# Get only main content (no headers/footers)
curl -H "X-Return-Format: markdown" \
     -H "X-No-Cache: true" \
     https://r.jina.ai/https://example.com

# With images as markdown
curl -H "X-With-Images: true" \
     https://r.jina.ai/https://example.com

4. Grounding for AI Agents

Use as a tool for AI agents to research the web:

def web_read(url: str) -> str:
    resp = requests.get(f"https://r.jina.ai/{url}")
    return resp.text

# Agent can now read any web page
content = web_read("https://docs.python.org/3/library/asyncio.html")

5. Batch Processing

urls = [
    "https://r.jina.ai/https://page1.com",
    "https://r.jina.ai/https://page2.com",
    "https://r.jina.ai/https://page3.com",
]
# Process in parallel for RAG ingestion

Use Cases

Use Case How
RAG Pipeline Extract clean text from source URLs
AI Research Agent Read documentation and articles
Content Scraping Get structured content without Playwright
Summarization Clean input for LLM summarizers

Rate Limits

Tier Rate Price
Free 20 RPM $0
Paid 200 RPM From $10/mo

FAQ

Q: Is it really free? A: Yes, 20 requests per minute free. No API key required for basic use.

Q: How does it handle JavaScript-rendered pages? A: Jina Reader renders JavaScript before extraction, handling SPAs and dynamic content.

Q: Can I self-host? A: Yes, the reader is open-source and can be self-hosted.

🙏

Source & Thanks

Created by Jina AI. Licensed under Apache 2.0.

jina-ai/reader — 20k+ stars

Discussion

Sign in to join the discussion.
No comments yet. Be the first to share your thoughts.

Related Assets