# AssetFeed AI Detection

AssetFeed AI Detection — a hosted MCP server with two tools that estimate how much of an English text or a public page reads as machine-written. Handy before you publish someone else's draft.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 8 repo stars
- Author: assetfeed
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/assetfeed/assetfeed-mcp/tree/HEAD/ai-detection
- Updated: 2026-10-29
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/mcp/assetfeed-ai-detection

## What it does

The endpoint is `https://api.assetfeed.com/mcp/ai-detection` and it answers two calls. `detect_ai_text` scores pasted prose passage by passage; `detect_ai_url` pulls a public page and runs the same check on the prose it finds there. Both are read-only. You don't invoke them by hand: ask your assistant a normal question about a draft and it picks the tool.

Nothing gets installed locally, since the service is hosted. Access works either through an OAuth sign-in with an AssetFeed account or with an API key placed in a Bearer header in your client config. Tool calls draw on AssetFeed credits, so a long review session has a cost attached.

Two limits shape how you use it. Input has to be English, and the text should land between 50 and 30,000 words. What comes back is an estimate: stiff formal prose from a human can end up flagged, so read the marked passages yourself before acting on them.

## Requirements
- Remote server: `https://api.assetfeed.com/mcp/ai-detection`

## Install

### Claude Code (native platform)

**Platform CLI: remote server**
```bash
claude mcp add --transport http ai-detection https://api.assetfeed.com/mcp/ai-detection
```

### Codex

**Platform CLI: remote server**
```bash
codex mcp add ai-detection --url https://api.assetfeed.com/mcp/ai-detection
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "ai-detection": {
            "url": "https://api.assetfeed.com/mcp/ai-detection"
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "ai-detection": {
            "type": "http",
            "url": "https://api.assetfeed.com/mcp/ai-detection"
        }
    }
}
```

### Gemini CLI

**Platform CLI: remote server**
```bash
gemini mcp add -t http ai-detection https://api.assetfeed.com/mcp/ai-detection
```

## When to use it
- Check a draft for machine-written passages before it goes live
- Scan a public page by URL and see which parts look generated
- Find the paragraphs in a long document that read as AI output
- Get a second opinion on text that arrived from a freelancer

## Example prompts
- Run `detect_ai_text` on the draft I'm pasting and show me the flagged passages.
- Fetch the page at the address I'll give you and check it with `detect_ai_url`.
- Which paragraphs of this article look AI-written? Give me the breakdown by passage.

## Similar
- [ai-detector](https://affpapa.org/en/nevibecode/skills/ai-detector.md) — skill · 1100 installs
- [Writing Style Checker](https://affpapa.org/en/nevibecode/mcp/writing-style-checker.md) — MCP server · ★ 9 repo stars
- [Sentiment Analyzer — Emotions, Confidence & Key Phrases](https://affpapa.org/en/nevibecode/mcp/sentiment-analyzer-emotions-confidence-key-phrases.md) — MCP server · 4789 installs
- [ChromaDB Remote MCP Server](https://affpapa.org/en/nevibecode/mcp/chromadb-remote-mcp-server.md) — MCP server · ★ 12 repo stars
- [provenanceai](https://affpapa.org/en/nevibecode/mcp/provenanceai.md) — MCP server · 236 installs
- [dhdna-profiler](https://affpapa.org/en/nevibecode/skills/dhdna-profiler.md) — skill · 2100 installs

From the same set: [assetfeed/assetfeed-mcp](https://affpapa.org/en/nevibecode/by/assetfeed/assetfeed-mcp.md) — 2 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
