Was kannst du mit BanProof AI machen?

BanProof AI — MCP Server

Audit TikTok Shop and Amazon affiliate video scripts for policy violations before creators record.

What it does

BanProof AI scans video scripts against TikTok Shop content policies, Amazon Associates Operating Agreement, and FTC disclosure guidelines. It flags the exact phrases that rack up violation points or trigger account strikes, and returns safe rewrites that keep the hook and CTA intact.

MCP tool: audit_script
Input: script (string) — the full video script text
Output: flagged phrases, violation categories, safe rewrites, overall risk level (safe / elevated / high)

Connect

Hosted endpoint: https://banproof.io/mcp

Auth: OAuth 2.0 via Supabase. Create a free account at banproof.io — 3 audits/month, no credit card required.

Compatible with Claude, ChatGPT, Cursor, and any MCP-compatible client.

Example

Input:

This serum will completely cure your acne in 3 days — guaranteed results or your money back. FDA approved and clinically proven.

Output:

3 violations detected (risk: high)
1. [Absolute medical claim] "cure your acne in 3 days" → "support clearer-looking skin over time"
2. [Guarantee claim] "guaranteed results or your money back" → "so many creators love how it performs"
3. [False certification] "FDA approved" → "made with carefully selected ingredients"

Pricing

Plan	Price	Audits
Free	$0/month	3/month
Creator	$19.99/month	50/month
Brand	$49.99/month	200/month, 5 seats

Links

Website: banproof.io
MCP endpoint: banproof.io/mcp
Pricing: banproof.io/pricing

Installation

BanProof AI zu deinem Client hinzufügen. Wähl den, den du nutzt.

claude mcp add --transport http banproof-ai https://banproof.io/mcp

codex mcp add banproof-ai --url https://banproof.io/mcp

{
  "mcpServers": {
    "banproof-ai": {
      "url": "https://banproof.io/mcp"
    }
  }
}

Add to `~/.cursor/mcp.json`, or `.cursor/mcp.json` for a single project.

{
  "servers": {
    "banproof-ai": {
      "type": "http",
      "url": "https://banproof.io/mcp"
    }
  }
}

Add to `.vscode/mcp.json` in your workspace.

{
  "mcpServers": {
    "banproof-ai": {
      "url": "https://banproof.io/mcp"
    }
  }
}

Add to `claude_desktop_config.json`, then restart Claude Desktop.

{
  "mcpServers": {
    "banproof-ai": {
      "serverUrl": "https://banproof.io/mcp"
    }
  }
}

Add to `~/.codeium/windsurf/mcp_config.json`.

Score

39 / 100

Unvollständig

Dokumentation17/25
Pflege19/25
Vertrauen6/20
Funktionsumfang0/15
Installation12/15

Documents what it does and how to connect
Has a resolvable package or endpoint
Exposes at least one tool, prompt or resource
README has substantive content
Includes a code example
Documents its configuration
Mentions credentials or security posture
Last commit 21 days ago
Has a release history
Repository is not archived
No licence detected
Namespace verified in the official MCP registry
Claimed by its owner
Published under an organisation
0 tool(s) documented
Provides prompt templates
Provides resources
6 documented install method(s)
Published to a package registry
Offers a hosted endpoint — no local install

Vollständige Kriterien lesen →

Versionsverlauf

Versionen	Veröffentlicht
1.0.0Aktuell	12. Aug. 2026