# Pangram MCP Editorial Tools

An MCP (Model Context Protocol) server that integrates [Pangram's AI attribution APIs](https://pangram.com) into professional writing workflows.

Designed for **editorial review, transparency, and quality assurance** when AI-assisted tools are used in journalism, research, and enterprise content creation.

## Use Cases

- **Newsrooms & Publishers** — Audit AI attribution before publication
- **Academic Writers** — Verify transparency requirements for submissions
- **Enterprise Content Teams** — QA workflows for AI-assisted documentation
- **Legal & Compliance** — Attribution audits for authored materials

## Features

| Tool | Purpose |
|------|---------|
| `pangram_attribution_audit` | Detailed attribution and segment analysis for transparency audits |
| `pangram_quick_snapshot` | Quick attribution snapshot for editorial review |

## Quick Start

### 1. Install

```bash
git clone https://github.com/nicholasgriffintn/pangram-mcp-editorial-tools.git
cd pangram-mcp-editorial-tools
npm install
npm run build
```

### 2. Get Your Pangram API Key

1. Go to [pangram.com](https://pangram.com)
2. Log in to your dashboard
3. Click **API** in the header
4. Copy your API key

### 3. Configure Claude Desktop

Add to your Claude Desktop config (`~/Library/Application Support/Claude/claude_desktop_config.json` on macOS):

```json
{
  "mcpServers": {
    "pangram-editorial": {
      "command": "node",
      "args": ["/absolute/path/to/pangram-mcp-editorial-tools/dist/index.js"],
      "env": {
        "PANGRAM_API_KEY": "your-api-key-here"
      }
    }
  }
}
```

### 4. Restart Claude Desktop

The Pangram editorial tools will now be available in all your conversations.

## Usage Examples

Once connected, use naturally in Claude:

> "Run an attribution audit on this article before I submit it"

> "Quick transparency check on this draft"

> "Analyze the authorship segments in my report"

## Tools Reference

### `pangram_attribution_audit`

Comprehensive attribution analysis providing:
- Overall authorship assessment
- Segment-by-segment attribution breakdown
- Confidence metrics per section
- Transparency report suitable for editorial review

**Parameters:**
- `text` (required): Content to analyze (minimum 50 words)
- `response_format` (optional): `"markdown"` (default) or `"json"`

### `pangram_quick_snapshot`

Fast attribution check for iterative editorial workflows:
- Summary authorship indicator
- Attribution percentage
- Quick review status

**Parameters:**
- `text` (required): Content to analyze (minimum 50 words)

## Requirements

- Node.js 18+
- Pangram API key ([pangram.com](https://pangram.com))
- Claude Desktop or any MCP-compatible client

## API Note

Pangram's API is priced separately from their web dashboard subscription. See [pangram.com/solutions/api](https://pangram.com/solutions/api) for details.

## Development

```bash
npm install
npm run build
npm run dev  # watch mode
```

## About

This project addresses the growing need for attribution transparency in professional writing workflows. As AI-assisted authorship becomes standard practice in journalism, research, and enterprise content, tools that provide clear attribution analysis support responsible disclosure and editorial integrity.

## License

MIT

## Contributing

Contributions welcome. Please ensure any additions maintain the project's focus on editorial transparency and professional quality assurance.