Text Utilities for AI Applications

stable

text.utils.v1

The Text Utilities MCP server provides essential text processing capabilities for AI applications, chatbots, and automation workflows. Features 19 specialized tools covering text analysis, encoding, formatting, extraction, and HTML manipulation. Perfect for preprocessing text data, content analysis, and natural language processing pipelines.

Pricing

0.5 credits

Tools

19 available

Microsoft 365 Copilot Ready

This tool integrates seamlessly with Microsoft 365 Copilot, enabling enterprise users to extend their AI capabilities across Office applications.

Enterprise Use Cases:

•Analyze document statistics in Word and SharePoint
•Detect language of incoming emails in Outlook
•Generate URL-safe filenames for Teams attachments
•Extract emails and URLs from meeting transcripts
•Convert between naming conventions in code documentation

Available Tools

`text_stats`

Comprehensive text statistics including word, character, sentence, and paragraph counts

Input Parameters

text- string (required) - The text to analyze

Response Format

words- number - Word count

characters- number - Character count

charactersNoSpaces- number - Character count excluding spaces

sentences- number - Sentence count

paragraphs- number - Paragraph count

`reading_time`

Estimate reading time based on average reading speed

Input Parameters

text- string (required) - The text to analyze

wordsPerMinute- number (optional) - Reading speed (default: 200)

Response Format

minutes- number - Estimated reading time in minutes

seconds- number - Estimated reading time in seconds

`detect_language`

Detect language using statistical analysis (supports 11 languages: English, Spanish, French, German, Italian, Portuguese, Chinese, Japanese, Korean, Arabic, Russian)

Input Parameters

text- string (required) - The text to analyze (minimum 10 characters)

Response Format

language- string - Language code (e.g., "en", "es", "fr", "zh", "ja", "ko", "ar", "ru")

confidence- number - Confidence score (0-1)

languageName- string - Full language name

`detect_encoding`

Detect text encoding using chardet library

Input Parameters

text- string (optional) - Text to analyze

data- string (optional) - Base64-encoded data to analyze

Response Format

encoding- string - Detected encoding (e.g., "utf-8", "latin-1")

confidence- number - Confidence score (0-1)

`convert_encoding`

Convert text between different character encodings

Input Parameters

text- string (required) - The text to convert

fromEncoding- string (optional) - Source encoding (default: "utf-8")

toEncoding- string (optional) - Target encoding (default: "utf-8")

Response Format

text- string - Converted text

success- boolean - Conversion success status

`url_encode`

URL encode text for safe transmission in URLs

Input Parameters

text- string (required) - The text to encode

Response Format

encoded- string - URL-encoded text (e.g., "hello world" → "hello%20world")

`url_decode`

Decode URL-encoded text

Input Parameters

text- string (required) - The URL-encoded text to decode

Response Format

decoded- string - Decoded text

`base64_encode`

Base64 encode text

Input Parameters

text- string (required) - The text to encode

Response Format

encoded- string - Base64-encoded text

`base64_decode`

Decode Base64-encoded text

Input Parameters

text- string (required) - The Base64-encoded text to decode

Response Format

decoded- string - Decoded text

`slugify`

Convert text to URL-safe slug (lowercase, hyphens, no special characters)

Input Parameters

text- string (required) - The text to slugify

Response Format

slug- string - URL-safe slug (e.g., "My Blog Post!" → "my-blog-post")

`case_convert`

Convert between case styles: snake_case, camelCase, PascalCase, kebab-case, SCREAMING_SNAKE_CASE

Input Parameters

text- string (required) - The text to convert

to- string (required) - Target case style (snake_case, camelCase, PascalCase, kebab-case, SCREAMING_SNAKE_CASE)

Response Format

converted- string - Converted text

`normalize_unicode`

Normalize Unicode text to standard forms (NFC, NFD, NFKC, NFKD)

Input Parameters

text- string (required) - The text to normalize

form- string (optional) - Normalization form: NFC, NFD, NFKC, or NFKD (default: "NFC")

Response Format

normalized- string - Normalized text

`truncate`

Smart truncate with ellipsis, respecting word boundaries

Input Parameters

text- string (required) - The text to truncate

maxLength- number (optional) - Maximum length (default: 100)

suffix- string (optional) - Suffix to add (default: "...")

Response Format

truncated- string - Truncated text with suffix

`substring`

Extract substring by position

Input Parameters

text- string (required) - The source text

start- number (optional) - Start position (default: 0)

end- number (optional) - End position (default: end of string)

Response Format

substring- string - Extracted substring

`extract_urls`

Extract all URLs from text (supports http:// and https://)

Input Parameters

text- string (required) - The text to extract URLs from

Response Format

urls- array - List of extracted URLs

`extract_emails`

Extract all email addresses from text

Input Parameters

text- string (required) - The text to extract emails from

Response Format

emails- array - List of extracted email addresses

`strip_html_tags`

Remove all HTML tags and decode HTML entities

Input Parameters

text- string (required) - HTML text to clean

Response Format

text- string - Plain text with HTML removed

`escape_html`

Escape HTML entities for safe display (prevents XSS)

Input Parameters

text- string (required) - The text to escape

Response Format

escaped- string - HTML-escaped text

`unescape_html`

Unescape HTML entities back to original characters

Input Parameters

text- string (required) - The HTML-escaped text to unescape

Response Format

unescaped- string - Unescaped text

Common Use Cases

Text analysis and statistics for content management

Multi-language content detection and routing

URL slug generation for blogs and CMSs

Variable name and identifier conversion

Text encoding detection and conversion

Email and URL extraction from text

HTML content cleaning and manipulation

Base64 and URL encoding for data transmission

Pricing

Pricing Model

Fixed rate per operation

0.5 credits per tool invocation

Ready to Get Started?

Integrate Text Utilities for AI Applications into your AI applications today

View Pricing API Documentation

Text Utilities for AI Applications

Category

Pricing

Tools

Microsoft 365 Copilot Ready

Enterprise Use Cases:

Available Tools

text_stats

Input Parameters

Response Format

reading_time

Input Parameters

Response Format

detect_language

Input Parameters

Response Format

detect_encoding

Input Parameters

Response Format

convert_encoding

Input Parameters

Response Format

url_encode

Input Parameters

Response Format

url_decode

Input Parameters

Response Format

base64_encode

Input Parameters

Response Format

base64_decode

Input Parameters

Response Format

slugify

Input Parameters

Response Format

case_convert

Input Parameters

Response Format

normalize_unicode

Input Parameters

Response Format

truncate

Input Parameters

Response Format

substring

Input Parameters

Response Format

extract_urls

Input Parameters

Response Format

extract_emails

Input Parameters

Response Format

strip_html_tags

Input Parameters

Response Format

escape_html

Input Parameters

Response Format

unescape_html

Input Parameters

Response Format

Common Use Cases

Pricing

Pricing Model

Ready to Get Started?

`text_stats`

`reading_time`

`detect_language`

`detect_encoding`

`convert_encoding`

`url_encode`

`url_decode`

`base64_encode`

`base64_decode`

`slugify`

`case_convert`

`normalize_unicode`

`truncate`

`substring`

`extract_urls`

`extract_emails`

`strip_html_tags`

`escape_html`

`unescape_html`