MCP Server

x402-scraper-api

io.github.ihen404/x402-scraper-api
Search & Research Public & reachable MCP 2025-11-25

What this MCP does

Scrapes public web pages and returns parsed, clean text content.

crawl
Recursively crawl pages up to a given depth with page limits and domain scoping
Input schema
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['url'], 'properties': {'url': {'type': 'string', 'description': 'Seed URL for crawling'}, 'maxDepth': {'type': 'number', 'description': 'Maximum crawl depth'}, 'maxPages': {'type': 'number', 'description': 'Maximum total pages to crawl'}}, 'additionalProperties': False}
extract
Extract structured data from a specific URL or CSS selector using an AI schema instruction
Input schema
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['url', 'instruction'], 'properties': {'url': {'type': 'string', 'description': 'Target URL to scrape'}, 'timeout': {'type': 'number', 'description': 'Page load timeout in milliseconds'}, 'selector': {'type': 'string', 'description': 'Optional CSS selector to target a specific container element'}, 'instruction': {'type': 'string', 'description': 'Extraction instruction or description'}}, 'additionalProperties': False}
pdf
Generate a clean downloadable PDF document snapshot of a target URL
Input schema
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['url'], 'properties': {'url': {'type': 'string', 'description': 'Target URL to convert to PDF'}, 'format': {'type': 'string', 'description': 'Paper format e.g. Letter, A4'}}, 'additionalProperties': False}
render
Render a JavaScript/SPA-heavy website with optional element wait selectors
Input schema
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['url'], 'properties': {'url': {'type': 'string', 'description': 'Target URL to render'}, 'waitForSelector': {'type': 'string', 'description': 'Optional CSS selector to wait for'}}, 'additionalProperties': False}
screenshot
Capture a visual screenshot of a target URL with custom viewport settings
Input schema
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['url'], 'properties': {'url': {'type': 'string', 'description': 'Target URL to capture'}, 'width': {'type': 'number', 'description': 'Viewport width'}, 'height': {'type': 'number', 'description': 'Viewport height'}, 'fullPage': {'type': 'boolean', 'description': 'Whether to capture full page'}}, 'additionalProperties': False}
search_rag
Perform semantic search / RAG retrieval against a target URL using a natural language query
Input schema
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['url', 'query'], 'properties': {'url': {'type': 'string', 'description': 'Target URL to scrape and query against'}, 'query': {'type': 'string', 'description': 'Natural language search query or question'}}, 'additionalProperties': False}
Removed
scrape
Oct. 4, 2026, 2:40 a.m.
Added
render
Oct. 4, 2026, 2:40 a.m.
Added
search_rag
Oct. 4, 2026, 2:40 a.m.
Added
pdf
Oct. 4, 2026, 2:40 a.m.
Added
screenshot
Oct. 4, 2026, 2:40 a.m.
Added
crawl
Oct. 4, 2026, 2:40 a.m.
Added
extract
Oct. 4, 2026, 2:40 a.m.
Added
scrape
Oct. 2, 2026, 2:40 a.m.