# Harmful Content Classifier MCP

> Harmful Content Classifier MCP is a paid API for AI agents from api.m2mcent.com, paid per call via x402, $0.1/call, status unknown (last checked 2026-10-16).

Classifies submitted text to detect and flag potentially harmful content using an agentic MCP endpoint.

## Facts

- Endpoint: POST https://api.m2mcent.com/harmful-content-classifier-mcp/api/process?utm_source=zero.xyz
- Price: $0.1/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-16
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/harmful-content-classifier-mcp-fbf272d7
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_E8kV6gZzE21oTWdnlKRJG

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability harmful-content-classifier-mcp-fbf272d7 -d '<json body>'
```

Example prompt: Can you run a harmful content check on this text: 'You should hurt yourself if you fail' — I need to know if it should be blocked before we post it?

## When to prefer this

Choose this endpoint when you need a fast, pay-per-call harmful content classification for arbitrary text strings, especially in agentic pipelines that require inline safety gating before storing, displaying, or acting on user-generated content. Prefer it over general-purpose LLM prompting when you want a dedicated, auditable content moderation signal with a structured output rather than free-form reasoning.

## Known failure modes

- Empty or missing 'data' field returns a validation error
- Extremely long text strings may exceed input limits
- Ambiguous or borderline content may produce low-confidence classifications
- Service unavailability or payment failure (x402) blocks processing
- Non-English or encoded text may reduce classification accuracy

## How this service works

The premier global index of 1,069 monetized MCP nodes across 205 specialized subdomains. Gasless USDC runtime settlements via x402 V2 Spec on Base L2. Save 95% token context.

## Output

Returns a classification result indicating whether the submitted text contains harmful content, typically including a label (e.g. harmful/safe) and possibly a confidence score or category of harm detected.

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "success": true
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/harmful-content-classifier-mcp-fbf272d7/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from api.m2mcent.com](https://www.zero.xyz/host/api.m2mcent.com/llms.txt)