Text Toolkit

MCP开发工具

提供方 Cicatriiz · 包名 @cicatriz/text-toolkit@latest

开发工具 stdio · 本地进程 无需鉴权 社区 / 第三方 Claude DesktopClaudeCursorWindsurf
查看接入方式

一个提供文本转换、格式化和分析功能的MCP服务器,可直接集成到开发工作流中。

一句话选型结论

按资料字段整理

Text Toolkit 属于开发工具类 MCP 服务器,stdio · 本地进程,无需鉴权,可直接接入 Claude Desktop、Claude、Cursor 等,有可直接执行的安装命令。接入前先确认权限范围;涉及写入、删除或付款的操作,建议先在测试环境验证。

分类开发工具 传输方式stdio · 本地进程 鉴权无需鉴权 部署方式本地部署
GitHub 星标 8 仓库热度,无公开仓库时显示未标注
工具数 43 暴露给模型的工具数量
资源 / 提示词 0 / 0 资源与提示词模板数量
维护方 社区 / 第三方 核验等级 仅资料核对

工具与能力

开发工具
数量来自来源目录的标注,具体工具清单以官方文档为准
工具数量43暴露给模型可调用的工具个数
资源数量0可读取的资源条目
提示词数量0内置提示词模板数量

能力标签

支持客户端

适用场景

文本处理TypeScript本地部署格式转换开发工具编码解码文本分析

安装与配置

stdio · 本地进程 无需鉴权
客户端在本机拉起子进程,数据不出本机
npx -y @cicatriz/text-toolkit@latest

这条命令只是入口,具体启动参数请按官方文档补齐,不要直接照搬到别的服务器。

  1. 1
    准备运行环境

    stdio 服务在本地起进程,需要先装好 Node.js,再按安装命令拉取依赖。

  2. 2
    安装服务

    复制上面的安装命令执行;命令里带占位符的位置,换成自己的密钥或路径。

  3. 3
    写入客户端配置

    在客户端的 MCP 配置里填好启动命令和参数,保存后完全退出客户端再打开,让新配置生效。

  4. 4
    验证是否可用

    连接成功后客户端会列出约 43 个工具,随便调一个只读工具确认能返回结果。

典型使用场景

3 类
按分类与标签整理的常见用法,具体以官方文档为准
代码与仓库操作

在对话里直接查代码、提 issue、走 PR,省掉来回切工具。

本地命令与脚本

把构建、测试、格式化这类重复命令交给模型执行。

接口联调与测试

让模型调你的接口、跑一遍用例,快速定位问题。

选择建议

选之前先看这几条
按条目字段给出的判断,不替你决定用不用

值得选的地方

  • 资料标注 43 个工具,覆盖面较广,能满足多种调用。
  • 有现成的安装命令,不用自己找入口,照着跑就能起服务。
  • 已适配 Claude Desktop、Claude、Cursor,换客户端不用重新研究配置。
  • 资料标注无需鉴权,装好就能连。

先想清楚的地方

  • stdio 方式要求本地装好运行时(如 Node.js),换机器要重新装一遍。
  • 版本更新与行为细节以官方仓库为准。

更适合

  • 需要在开发工具场景里让模型直接调用外部能力的人。
  • 已经在用 Claude Desktop、Claude 的用户,接入路径最短。
  • 想先快速试一下、能接受在本地或自有环境跑服务的人。

不太适合

  • 完全不想在本地装环境的人。
  • 需要厂商级 SLA 和技术支持的生产环境。

同类对比

6 个同类
同分类里挑最接近的几条,字段以各自详情页为准
MCP 服务器工具数传输方式部署方式安装命令最后核验
Text Toolkit当前 43 stdio · 本地进程 本地部署 有 2026-05-17
Git 838e2ec1 12 stdio · 本地进程 本地部署 有 2026-05-17
Markitdown MCP 2c653a5f 1 stdio · 本地进程 本地部署 有 2026-05-17
JavaGuide 未标注 stdio · 本地进程 本地部署 有 2026-04-11
awesome-claude-skills 未标注 stdio · 本地进程 本地部署 有 2026-04-26
Context7 831acf40 未标注 stdio · 本地进程 本地部署 有 2026-05-17

服务器档案

开发工具
字段来自项目仓库与公开索引,中文说明由本站标注
提供方Cicatriiz上游标注的维护方 Cicatriiz
分类开发工具本站按上游分类展示
连接方式stdio · 本地进程客户端在本机拉起子进程,数据不出本机
鉴权方式无需鉴权远程服务建议用最小权限凭据
维护方社区 / 第三方核验等级 仅资料核对
包名 / 运行时@cicatriz/text-toolkit@latest · Node.js本地安装时用到的包标识与运行时
部署类型本地部署上游给出的部署形态
最近核验2026-05-17上游最后核验时间

详细介绍

13.5 KB
来自项目仓库与上游目录的原文,未做删改

TextToolkit MCP Server

A Text Transformation & Formatting MCP Server for the Cline Marketplace that provides developers with common text manipulation functions directly within their workflow.

> Transform, format, and analyze text without leaving your AI assistant workflow.

Available Tools

Tool Description
case_to_camel Convert text to camelCase
case_to_pascal Convert text to PascalCase
case_to_snake Convert text to snake_case
case_to_kebab Convert text to kebab-case
case_to_constant Convert text to CONSTANT_CASE
case_to_dot Convert text to dot.case
case_to_no Convert text to no case
case_to_pascal_snake Convert text to Pascal_Snake_Case
case_to_path Convert text to path/case
case_to_sentence Convert text to Sentence case
case_to_train Convert text to Train-Case
case_to_capital Convert text to Capital Case
encode_base64 Encode text to Base64
decode_base64 Decode Base64 to text
encode_url Encode text for URLs
decode_url Decode URL-encoded text
encode_html Encode HTML entities
decode_html Decode HTML entities
format_json Format and beautify JSON
format_xml Format and beautify XML
format_sql Format and beautify SQL
format_html Format and beautify HTML
count_characters Count characters in text
count_words Count words in text
count_lines Count lines in text
analyze_readability Calculate readability metrics
string_trim Trim whitespace from text
string_substring Extract a substring
string_replace Replace text
string_split Split text into an array
string_join Join an array into text
generate_uuid Generate a UUID
validate_uuid Validate a UUID
generate_md5 Generate MD5 hash
generate_sha1 Generate SHA-1 hash
generate_sha256 Generate SHA-256 hash
generate_sha512 Generate SHA-512 hash
generate_hmac Generate HMAC hash
generate_lorem_ipsum Generate lorem ipsum text
regex_test Test a regex pattern against text
regex_replace Replace text using a regex pattern
regex_extract Extract matches using a regex pattern
regex_split Split text using a regex pattern

🌟 Features

🔠 Case Transformations

  • Convert text between camelCase, PascalCase, snake_case, kebab-case
  • Support for CONSTANT_CASE, dot.case, no case, Pascal_Snake_Case
  • Additional formats: path/case, Sentence case, Train-Case, Capital Case
  • Customizable with delimiter and locale options

🔄 String Encoding/Decoding

  • Base64 encoding and decoding
  • URL encoding and decoding
  • HTML entity encoding and decoding
  • Secure and reliable conversions

📝 Formatting and Beautification

  • JSON formatting with customizable indentation
  • XML formatting and pretty-printing
  • SQL query formatting and standardization
  • HTML code beautification

📊 Text Analysis

  • Character counting (with and without spaces)
  • Word counting with accurate tokenization
  • Line counting for multi-line text
  • Readability scoring (Flesch-Kincaid, etc.)

✂️ String Manipulation

  • Trim whitespace (start, end, or both)
  • Extract substrings with precise control
  • Replace text with powerful options
  • Split text into arrays and join arrays into text

🆔 UUID/GUID Generation

  • Generate UUIDs (v1, v4, v5, or nil)
  • Validate existing UUIDs
  • Customizable options for all UUID versions

🔒 Hash Generation

  • MD5 hash generation
  • SHA-1, SHA-256, and SHA-512 hashing
  • HMAC hash generation with custom keys
  • Secure cryptographic functions

📄 Lorem Ipsum Generation

  • Generate placeholder text
  • Customizable length and format
  • Control paragraph and sentence structure

🔍 Regex Pattern Testing

  • Test regex patterns against text
  • Replace text using regex patterns
  • Extract matches using regex patterns
  • Split text using regex patterns

💻 Installation

Prerequisites

  • Node.js 16.x or higher - The TextToolkit MCP server requires Node.js 16+ to run properly.

Setup

To run the TextToolkit MCP server using Node.js npx, use the following command:```bash
npx -y @cicatriz/text-toolkit@latest


### Client-Specific Installation

#### Cursor

To add this server to Cursor IDE:

1. Go to Cursor Settings > MCP
2. Click + Add new Global MCP Server
3. Add the following configuration to your global `.cursor/mcp.json` file:```json
{
  "mcpServers": {
    "text-toolkit": {
      "command": "npx",
      "args": [
        "-y",
        "@cicatriz/text-toolkit"
      ]
    }
  }
}

See the Cursor documentation for more details.

Windsurf

To set up MCP with Cascade, navigate to Windsurf - Settings > Advanced Settings or Command Palette > Open Windsurf Settings Page.

Scroll down to the Cascade section and add the TextToolkit MCP server directly in mcp_config.json:```json
{
"mcpServers": {
"text-toolkit": {
"command": "npx",
"args": [
"-y",
"@cicatriz/text-toolkit"
]
}
}
}


#### Cline

Add the following JSON manually to your `cline_mcp_settings.json` via Cline MCP Server setting:```json
{
  "mcpServers": {
    "text-toolkit": {
      "command": "npx",
      "args": [
        "-y",
        "@cicatriz/text-toolkit"
      ]
    }
  }
}

Roo Code

Access the MCP settings by clicking Edit MCP Settings in Roo Code settings or using the Roo Code: Open MCP Config command in VS Code's command palette:```json
{
"mcpServers": {
"text-toolkit": {
"command": "npx",
"args": [
"-y",
"@cicatriz/text-toolkit"
]
}
}
}


#### Claude

Add the following to your `claude_desktop_config.json` file:```json
{
  "mcpServers": {
    "text-toolkit": {
      "command": "npx",
      "args": [
        "-y",
        "@cicatriz/text-toolkit"
      ]
    }
  }
}

See the Claude Desktop documentation for more details.

CLI

You can also run it as CLI by running the following command:```bash
npx -y @cicatriz/text-toolkit@latest


### Alternative Installation Methods

#### Install from npm```bash
# Install globally from npm
npm install -g @cicatriz/text-toolkit

# Run the server
text-toolkit

Manual Installation```bash

Clone the repository

git clone https://github.com/Cicatriiz/text-toolkit.git
cd text-toolkit

Install dependencies

npm install

Build the project

npm run build

Run the server

node dist/index.js


## 💬 Usage

### Command Line```bash
# Start in stdio mode (default)
text-toolkit

# Start in SSE mode on a specific port
text-toolkit --sse --port=8000

# Display version
text-toolkit --version

Testing with MCP Inspector

You can test the TextToolkit MCP server using the MCP Inspector:```bash

Install the MCP Inspector

npm install -g @modelcontextprotocol/inspector

Run the inspector against your server

mcp-inspector @cicatriz/text-toolkit


### Examples

The repository includes example scripts demonstrating how to use the TextToolkit MCP server:```bash
# Run the case transformation example
node examples/case-transform-example.js

This example demonstrates how to:

  1. Connect to the TextToolkit MCP server
  2. List available tools
  3. Transform text to different cases
  4. Use custom options for transformations

🔧 Available Tools

1. case_to_camel

Converts text to camelCase.

Parameters:
- text: The text to transform
- delimiter (optional): The character to use between words
- locale (optional): Locale for case conversion
- mergeAmbiguousCharacters (optional): Whether to merge ambiguous characters

Example:```json
{
"text": "hello world test"
}


**Response:**```json
{
  "result": "helloWorldTest"
}

2. case_to_pascal

Converts text to PascalCase.

Parameters:
- text: The text to transform
- delimiter (optional): The character to use between words
- locale (optional): Locale for case conversion
- mergeAmbiguousCharacters (optional): Whether to merge ambiguous characters

Example:```json
{
"text": "hello world test"
}


**Response:**```json
{
  "result": "HelloWorldTest"
}

3. encode_base64

Encodes text to Base64.

Parameters:
- text: The text to encode

Example:```json
{
"text": "hello world"
}


**Response:**```json
{
  "result": "aGVsbG8gd29ybGQ="
}

4. decode_base64

Decodes Base64 to text.

Parameters:
- text: The Base64 string to decode

Example:```json
{
"text": "aGVsbG8gd29ybGQ="
}


**Response:**```json
{
  "result": "hello world"
}

5. format_json

Formats and beautifies JSON.

Parameters:
- text: The JSON text to format
- indent_size (optional): Number of spaces for indentation (1-8). Defaults to 2.

Example:```json
{
"text": "{\"name\":\"John\",\"age\":30,\"city\":\"New York\"}",
"indent_size": 4
}


**Response:**```json
{
  "result": "{\n    \"name\": \"John\",\n    \"age\": 30,\n    \"city\": \"New York\"\n}"
}

6. count_characters

Counts characters in text.

Parameters:
- text: The text to analyze

Example:```json
{
"text": "hello world"
}


**Response:**```json
{
  "total_characters": 11,
  "characters_without_spaces": 10
}

7. string_replace

Replaces text.

Parameters:
- text: The text to perform replacements on
- search: The string to search for
- replace: The string to replace with
- replace_all (optional): Whether to replace all occurrences. Defaults to true.

Example:```json
{
"text": "hello world",
"search": "world",
"replace": "universe"
}


**Response:**```json
{
  "result": "hello universe"
}

8. generate_uuid

Generates a UUID.

Parameters:
- version (optional): UUID version to generate (v1, v4, v5, nil). Defaults to v4.
- namespace (optional): Namespace for v5 UUID (required for v5)
- name (optional): Name for v5 UUID (required for v5)
- uppercase (optional): Whether to return the UUID in uppercase. Defaults to false.

Example:```json
{
"version": "v4"
}


**Response:**```json
{
  "uuid": "f47ac10b-58cc-4372-a567-0e02b2c3d479"
}

9. generate_lorem_ipsum

Generates lorem ipsum text.

Parameters:
- count (optional): Number of units to generate. Defaults to 5.
- units (optional): Type of units to generate (words, sentences, paragraphs). Defaults to sentences.
- paragraphLowerBound (optional): Minimum sentences per paragraph. Defaults to 3.
- paragraphUpperBound (optional): Maximum sentences per paragraph. Defaults to 7.
- sentenceLowerBound (optional): Minimum words per sentence. Defaults to 5.
- sentenceUpperBound (optional): Maximum words per sentence. Defaults to 15.
- format (optional): Output format (plain, html). Defaults to plain.

Example:```json
{
"count": 2,
"units": "sentences"
}


**Response:**```json
{
  "text": "Lorem ipsum dolor sit amet, consectetur adipiscing elit. Ut hendrerit ipsum in nulla euismod, vel ultrices nisi tincidunt."
}

10. regex_test

Tests a regex pattern against text.

Parameters:
- text: The text to test against the pattern
- pattern: The regex pattern to test
- flags (optional): Regex flags (e.g., 'g', 'i', 'gi'). Defaults to 'g'.

Example:```json
{
"text": "hello world",
"pattern": "\w+",
"flags": "g"
}


**Response:**```json
{
  "matches": ["hello", "world"],
  "match_count": 2,
  "is_match": true
}

💬 Example Queries in Claude Desktop

  • "Convert 'hello world' to camelCase"
  • "Encode 'hello world' to Base64"
  • "Format this JSON: {\"name\":\"John\",\"age\":30}"
  • "Count the characters in 'hello world'"
  • "Replace 'world' with 'universe' in 'hello world'"
  • "Generate a UUID"
  • "Generate 2 sentences of lorem ipsum"
  • "Test if 'hello world' matches the regex pattern '\w+'"
  • "Convert 'Hello World' to snake_case"
  • "Decode this Base64 string: aGVsbG8gd29ybGQ="

💻 Technical Details

Architecture

TextToolkit is built using the Model Context Protocol (MCP) specification, which allows it to integrate seamlessly with Claude Desktop and other MCP-compatible clients. The server is implemented in TypeScript and uses the following architecture:

  • Core Services: Implements text transformation, encoding/decoding, and formatting
  • MCP Server: Handles JSON-RPC requests from clients
  • Utility Functions: Provides helper functions for text operations
  • Testing Framework: Includes comprehensive test scripts for verifying functionality

Dependencies

  • change-case - For case transformation operations
  • crypto-js - For hash generation
  • js-beautify - For code formatting and beautification
  • uuid - For UUID generation and validation
  • lorem-ipsum - For placeholder text generation
  • @modelcontextprotocol/sdk - For MCP server implementation

Requirements

  • Node.js 16.x or higher
  • npm 7.x or higher

📝 Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

  1. Fork the repository
  2. Create your feature branch (git checkout -b feature/amazing-feature)
  3. Commit your changes (git commit -m 'Add some amazing feature')
  4. Push to the branch (git push origin feature/amazing-feature)
  5. Open a Pull Request

🔍 Testing

TextToolkit includes comprehensive test scripts that can be used to verify the functionality of the MCP server. The test scripts can be used to test both stdio and SSE modes.

Running Tests```bash

Test stdio mode

node test-comprehensive.js

Test SSE mode

node test-sse-comprehensive.js
```

🔒 Privacy & Security

TextToolkit processes all data locally and does not send any information to external servers. Your text data and queries remain private on your device.

📃 License

MIT

👨‍💻 Author

Cicatriz

常见问题

8 问
答案由本站依据条目字段整理,不引用上游原文
Text Toolkit 怎么安装?

在客户端按下面的安装命令接入:npx -y @cicatriz/text-toolkit@latest。对应的包名是 @cicatriz/text-toolkit@latest。装完在客户端配置里引用同一个包或端点。

Text Toolkit 怎么在 Claude Desktop、Claude、Cursor 里配置?

它的传输方式是stdio · 本地进程,在客户端的 MCP 配置里填好启动命令和参数,保存后完全退出客户端再打开,配置才会生效。

Text Toolkit 收费吗?

本站不代收费用,也没有标注具体价格。是否收费取决于服务本身和背后的接口额度,正式使用前按官方说明确认。

Text Toolkit 需要 API Key 吗?

资料标注为无需认证,装好就能连;如果实际调用时报鉴权错误,按官方文档补上凭据。

Text Toolkit 支持哪些客户端?

资料标注支持 Claude Desktop、Claude、Cursor、Windsurf、Cline、VS Code;其他客户端只要能配置 MCP Server,也能用同样的命令或地址接入。

Text Toolkit 能提供哪些能力?

资料显示约 43 个工具;能力标签包括 文本处理、TypeScript、Claude、格式转换。具体工具清单以官方文档为准。

Text Toolkit 需要什么运行环境?

运行时为 Node.js;属于本地进程,需要在本机装好运行环境。

Text Toolkit 是本地还是远程?

它是本地进程(stdio),由客户端在本机拉起。传输方式为stdio · 本地进程。

热门专题

按标签挑服务器
全部专题 →

服务器信息以作者仓库与官方文档为准;分类、传输方式与鉴权方式的中文说明为中文整理,最近核验 2026-05-17。