extract_text_only

MCP tool from MCP Web Scrape by mukul975

Extract plain text content without formatting or HTML

How to use it

extract_text_only is exposed by the MCP Web Scrape MCP server. Add the server to your MCP client (Claude Desktop, Cursor, Windsurf and others), and the extract_text_only tool becomes available to the model automatically. See the full listing for setup details and every tool this server provides.

Install MCP Web Scrape

$npx mcp-web-scrape@1.0.7

FULL MCP WEB SCRAPE LISTING

Other tools in MCP Web Scrape (39)

analyze_competitors

Analyze competitor websites for SEO and content insights

analyze_cookies

Analyze cookies and tracking mechanisms

analyze_page_speed

Analyze page loading speed and performance metrics

analyze_readability

Analyze text readability using various metrics (Flesch, Gunning-Fog, etc.)

Process multiple URLs efficiently

check_broken_links

Check for broken links and redirects on pages

check_privacy_policy

Analyze privacy policy compliance and coverage

check_ssl_certificate

Check SSL certificate validity and security details

check_url_status

Verify URL accessibility

classify_content

Classify content into categories and topics

Manage cached content

compare_content

Compare two pages for changes

Convert web pages to PDF format with customizable settings

detect_language

Detect the primary language of web page content

detect_tracking

Detect tracking scripts and privacy concerns

extract_contact_info

Discover emails, phone numbers, and addresses

extract_content

Convert HTML to clean Markdown with citations

extract_entities

Extract named entities (people, places, organizations)

Discover and parse RSS/Atom feeds

Extract form elements, fields, and validation rules

extract_headings

Analyze heading structure (H1-H6) for content hierarchy

Extract images with alt text and dimensions

extract_keywords

Extract important keywords and phrases from content

Get all links with filtering options

extract_schema_markup

Extract and validate schema.org structured data

extract_social_media

Find social media links and profiles

extract_structured_data

Parse JSON-LD, microdata, RDFa

Parse HTML tables with headers and structured data

generate_meta_tags

Generate optimized meta tags for SEO

generate_word_cloud

Generate word frequency analysis and word cloud data

get_cache_stats

View cache performance metrics

get_page_metadata

Extract title, description, author, keywords

Monitor website uptime and availability

scan_vulnerabilities

Scan pages for common security vulnerabilities

Search within page content

sentiment_analysis

Analyze sentiment and emotional tone of content

summarize_content

AI-powered content summarization

translate_content

Translate web page content to different languages

validate_robots

Check robots.txt compliance