MCP 服务器

TrueVoice MCP

Enables detection and elimination of AI slop in text, providing tools to analyze writing for overused phrases, structural issues, and verbosity, and offers human writing rules tailored to context.

README

TrueVoice MCP

Tools to eliminate AI slop from text

Model Context Protocol server with tools to detect and eliminate AI slop from text. Based on expert annotations from NLP writers and philosophers analyzing AI-generated text patterns.

What is AI Slop?

Low-quality AI text characterized by:

Information Utility: Low content density, irrelevant filler, factual errors
Style Quality: Repetitive structures, corporate clichés ("delve into", "leverage")
Structure: Excessive verbosity, poor coherence, formulaic patterns

Research foundation: arXiv:2509.19163v1

Quick Start

One-Click Install

Visit truevoice-mcp.kushagragolash.tech for one-click install buttons for Cursor, VS Code, Claude Code, and Claude Desktop.

Claude Code

claude mcp add --transport http truevoice https://truevoice-mcp.kushagragolash.tech/api/mcp

Claude Desktop

Open Settings > Connectors > Add custom server, paste:

https://truevoice-mcp.kushagragolash.tech/api/mcp

Any MCP Client

Add to your MCP configuration:

{
  "mcpServers": {
    "truevoice": {
      "url": "https://truevoice-mcp.kushagragolash.tech/api/mcp"
    }
  }
}

Local Development (stdio)

{
  "mcpServers": {
    "truevoice": {
      "command": "node",
      "args": ["/path/to/truevoice-mcp/dist/index.js"]
    }
  }
}

See Development for full local setup.

Available Tools

`get_human_writing_rules`

Get comprehensive anti-slop writing rules tailored to your context.

Parameters:

context (optional): Writing type (e.g., "technical blog", "email", "docs")

Example:

Get writing rules for a technical blog post

`check_for_slop`

Analyze text for AI slop indicators across three dimensions.

Parameters:

text (required): The text to analyze

Example:

Check this for slop: "In today's digital landscape, it's important to
note that we should leverage cutting-edge solutions to deliver a
seamless user experience..."

Returns:

⚠️ AI Slop Analysis

- Overused Phrases: Found AI clichés - landscape, it's important to note,
  leverage, cutting-edge, seamless
- Verbosity: Overly long sentences (avg 28.5 words)
- Word Complexity: Unnecessarily formal - "utilize" → "use"

Recommendation: Revise to be more concise, direct, and natural.

`get_slop_examples`

Get categorized examples of AI slop patterns to avoid.

Parameters:

category (optional): "phrases", "structure", "tone", or "all"

Example:

Show me phrase examples to avoid

What Gets Detected

Slop Phrases

"delve into" → "explore"
"leverage" → "use"
"it's important to note" → just state it
"robust", "seamless", "holistic", "paradigm shift"
"cutting-edge", "game changer", "synergy"

Structural Issues

Repetitive sentence starts (same word 3+ times)
Excessive bullet points and lists
Overly formal language for casual contexts
Long sentences (>25 words average)
Low lexical density (<40% unique words)

Research-Based Scoring

Text analyzed across three weighted dimensions:

Information Utility (β=0.06) - Content density, relevance
Style Quality (β=0.05) - Repetition, coherence, naturalness
Structure (β=0.05) - Verbosity, bias, flow

Development

Prerequisites

Node.js 18+
TypeScript 5.6+
npm or pnpm

Local Setup

git clone https://github.com/howdoiusekeyboard/truevoice-mcp
cd truevoice-mcp
npm install
npm run build

Available Scripts

npm run build - Compile TypeScript
npm run dev - Watch mode for development
npm start - Run stdio server locally
npx ultracite check - Lint check
npx ultracite fix - Auto-fix issues

Testing Locally

Test stdio transport (Claude Desktop):

npm run build
npm start
# Server runs on stdio, test with MCP inspector:
npx @modelcontextprotocol/inspector node dist/index.js

Test HTTP transport (Cursor/Web):

vercel dev
# Visit http://localhost:3000

Architecture

Project Structure

truevoice-mcp/
├── api/                    # Vercel serverless functions
│   ├── mcp.ts             # HTTP MCP endpoint (Streamable HTTP)
│   ├── index.ts           # API info page
│   ├── check.ts           # Slop detection API
│   ├── rules.ts           # Rules API
│   └── examples.ts        # Examples API
├── src/                    # Core MCP server
│   ├── index.ts           # stdio transport (Claude Desktop)
│   └── rules.ts           # Anti-slop taxonomy
├── public/
│   └── index.html         # Homepage/docs
└── dist/                   # Compiled output

Dual Transport Support

stdio Transport (Local/Claude Desktop):

Direct process communication
Low latency, persistent connection
Best for local development
Entry: dist/index.js

Streamable HTTP Transport (Vercel/Web):

POST-only mode (MCP 2024-11-05 spec)
Fully stateless, serverless-optimized
No SSE (Vercel 60s timeout limitation)
Auto-scaling on demand
Endpoint: /api/mcp

Technology Stack

Runtime: TypeScript 5.6+ with Node.js ESM modules
Validation: Zod schemas for type safety
Linting: Ultracite (Biome-powered)
MCP SDK: @modelcontextprotocol/sdk v1.19+
Deployment: Vercel serverless functions

Deploy Your Own

One-Click Deploy

Manual Deploy

npm install
vercel deploy --prod

Your MCP endpoint: https://your-project.vercel.app/api/mcp

Environment Variables

None required! Server works out of the box.

Usage Examples

In Claude Desktop

"Check my email draft for AI slop patterns"
"Get writing rules for professional documentation"
"Show me examples of phrases to avoid in blog posts"

As Writing Assistant

"Analyze this paragraph and suggest improvements:
[paste text]"

"Get human writing rules for casual Twitter posts,
then help me write a thread"

API Integration

# Check text for slop
curl -X POST https://truevoice-mcp.kushagragolash.tech/api/check \
  -H "Content-Type: application/json" \
  -d '{"text": "Your text here"}'

# Get writing rules
curl https://truevoice-mcp.kushagragolash.tech/api/rules?context=email