AI Agent, MCP & RAG Website-to-Markdown Semantic Chunker
Pricing
from $2.00 / 1,000 results
Go to Apify Store
AI Agent, MCP & RAG Website-to-Markdown Semantic Chunker
Converts any webpage or documentation page into clean GitHub-Flavored Markdown (preserving tables, code blocks, and heading hierarchy) + token-counted RAG semantic chunks with configurable overlap for LLMs, LangChain, LlamaIndex, and MCP servers.
Pricing
from $2.00 / 1,000 results
Rating
0.0
(0)
Developer
Huy Nguyen
Maintained by CommunityActor stats
0
Bookmarked
2
Total users
1
Monthly active users
19 hours ago
Last modified
Categories
Share
Converts any webpage or documentation page into clean GitHub-Flavored Markdown (preserving tables, code blocks, and heading hierarchy) + token-counted RAG semantic chunks with configurable overlap for LLMs, LangChain, LlamaIndex, and MCP servers.
Why Use AI Agent, MCP & RAG Website-to-Markdown Semantic Chunker?
- Production-Grade & Zero Maintenance: Built specifically for automated workflows in n8n, Make.com, Zapier, Clay, LangChain, and MCP servers.
- Pay-Per-Event (PPE) Transparent Pricing: Only $0.002 per enriched result (
$2.00 per 1,000 results) with structured JSON, CSV, and Excel export. - Fast & Lightweight: Uses high-concurrency HTTP parsing and structured JSON-LD / API discovery without expensive headless browser overhead.
Key Features
- Deep Structured Extraction: Automatically normalizes every output record against a strict dataset schema.
- Plug-and-Play API & Webhook Integration: Call directly via
POST https://api.apify.com/v2/acts/huynguyen-data-cloud~mcp-universal-web-reader/run-sync-get-dataset-items. - Built-in Data Hygiene: Deduplicates records, filters false positives, and computes actionable scoring metrics.
Quick Start (cURL / API)
curl -X POST "https://api.apify.com/v2/acts/huynguyen-data-cloud~mcp-universal-web-reader/run-sync-get-dataset-items?token=YOUR_APIFY_TOKEN" \-H "Content-Type: application/json" \-d '{"startUrls": [{"url": "https://apify.com"}], "chunkSizeTokens": 500, "chunkOverlapTokens": 60}'