# Copyleaks — how to use (mcp.ai)

Connect your Copyleaks account and use 6 tools for AI content generation straight from your AI agent. Connect with your own API key. Copyleaks provides plagiarism, AI content, image, video, moderation, and writing analysis APIs.

## Option A — via MCP (recommended)
Remote MCP endpoint (HTTP, streamable): `https://api.mcp.ai/p_copyleaks?ms=1787293380000`
Add it as a custom/remote MCP connector in your client (Claude, Cursor, VS Code…), then authenticate when prompted. Once connected, ask the agent to use the server's tools (e.g. `copyleaks_check_writing`).

## Option B — via direct REST API
Base URL: `https://api.mcp.ai/api/copyleaks`
Auth: `Authorization: Bearer sk_live_…` — create a workspace API key at https://mcp.ai/settings/api-keys
Discover endpoints: `GET https://api.mcp.ai/api/copyleaks/_endpoints`

### Endpoints
- `POST https://api.mcp.ai/api/copyleaks/check/writing` — Return grammar, mechanics, structure, word-choice, and readability feedback synchronously. By default this returns fixed sandbox mock output, not feedback on the submitted text; set sandbox=false for 
  - body: { text: string, sandbox?: boolean, scan_id: string, language?: string, score_weights?: object }
- `POST https://api.mcp.ai/api/copyleaks/detect/ai/text` — Classify text as human- or AI-written synchronously. By default this returns fixed sandbox mock output, not analysis of the submitted text; set sandbox=false for real analysis, which may consume AI de
  - body: { text: string, explain?: boolean, sandbox?: boolean, scan_id: string, language?: string, sensitivity?: integer }
- `POST https://api.mcp.ai/api/copyleaks/get/ai/text/credit/balance` — Return the connected account's separate AI Text Detector wallet balance.
- `POST https://api.mcp.ai/api/copyleaks/get/credit/balance` — Return the connected Copyleaks account's general plagiarism and authenticity scan credit balance.
- `POST https://api.mcp.ai/api/copyleaks/get/supported/metadata` — Return one public Copyleaks capability catalog: OCR languages, AI text file types, cross-language options, plagiarism file types, or writing correction definitions.
  - body: { language_code?: string, metadata_type: string }
- `POST https://api.mcp.ai/api/copyleaks/moderate/text` — Detect harmful-content labels in text synchronously. By default this returns fixed sandbox mock output, not moderation of the submitted text; set sandbox=false for real moderation, which may consume c
  - body: { text: string, sandbox?: boolean, scan_id: string, language?: string, label_ids?: string[] }

## Example prompts
- "What can I do in Copyleaks?"
- "Show me a summary of my Copyleaks account"

## More
- Page: https://mcp.ai/copyleaks
- Agent spec (llms.txt): https://mcp.ai/copyleaks/llms.txt
- Postman collection: https://mcp.ai/copyleaks/postman.json