wordly -app
MCP app for interactive text rewriting and grammar improvement visualization
claude mcp add --transport stdio arifszn-wordly-mcp-app npx -y wordly-mcp-app --stdio
How to use
Wordly is an MCP App that provides an interactive UI for visualizing multiple rewritten variations of text. It exposes a tool named visualize_rewrites, which AI assistants can call to generate and display several rewrite options in distinct styles, enabling side-by-side comparison and easy copying of preferred variations. To use Wordly within an MCP client, configure the server as shown in the README, then invoke the visualize_rewrites tool with the original text and a list of desired rewrite variations. The UI formats and renders the variations, allows switching between styles, comparing against the original, and copying any chosen rewrite with a single click.
Typical workflow: you provide an original sentence and a set of target rewrite intents (e.g., Professional, Clear & Conversational, Friendly). Wordly returns a structured set of rewritten texts, each tagged with its intent. The client UI then presents these options in an interactive panel where you can toggle between styles, view side-by-side comparisons with the original, and copy or insert a selected variation into your workspace. This makes it straightforward to apply tone and style adjustments across content batches.
How to install
Prerequisites:
- Node.js (LTS) and npm installed on your machine
- Internet access to fetch the Wordly MCP App via npx
Installation steps:
- Verify Node.js and npm: node -v npm -v
- Run the MCP server via npx (no global install required): npx -y wordly-mcp-app --stdio
- Confirm the app starts and establish the MCP client configuration as shown in the README (the command above is what the MCP client uses to launch Wordly).
- Optional: if you need a persistent setup, you can add the configuration to your MCP client config file under mcpServers with the same command and args.
Notes:
- The --stdio flag enables standard input/output communication between the MCP client and the Wordly app.
- If your environment blocks npx fetch, you may install the package locally first or use a containerized approach.
Additional notes
Tips and caveats:
- Ensure your MCP client configuration matches the example to initialize the Wordly app correctly.
- The visualize_rewrites tool expects an original_text and a variations array with intent and text fields. Provide diverse intents to generate a broad set of styles.
- If you encounter network restrictions, consider using a local npm cache or a containerized run of the app.
- Since Wordly is invoked via npx, you don’t need a global install; the command will fetch the package on demand.
- If you want to customize default variation intents or add more styles, adjust the variations payload in your tool call accordingly.
Related MCP Servers
context7
Context7 MCP Server -- Up-to-date code documentation for LLMs and AI code editors
obsidian -tools
Add Obsidian integrations like semantic search and custom Templater prompts to Claude or any MCP client.
MiniMax -JS
Official MiniMax Model Context Protocol (MCP) JavaScript implementation that provides seamless integration with MiniMax's powerful AI capabilities including image generation, video generation, text-to-speech, and voice cloning APIs.
mcp-bundler
Is the MCP configuration too complicated? You can easily share your own simplified setup!
akyn-sdk
Turn any data source into an MCP server in 5 minutes. Build AI-agents-ready knowledge bases.
promptboard
The Shared Whiteboard for Your AI Agents via MCP. Paste screenshots, mark them up, and share with AI.