# Hallucination Detector MCP

> Hallucination Detector MCP is a paid API for AI agents from api.m2mcent.com, paid per call via x402, $0.3/call, status unknown (last checked 2026-09-15).

Analyzes text to detect hallucinations, factual inconsistencies, or unsupported claims generated by AI models

## Facts

- Endpoint: POST https://api.m2mcent.com/hallucination-detector-mcp/api/process
- Price: $0.3/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/hallucination-detector-mcp-22dc8c2e
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_vme9JOm1MalzLE3sCBele

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 hallucination-detector-mcp-22dc8c2e -d '<json body>'
```

Example prompt: Check this AI-generated response for hallucinations and flag any unsupported or fabricated claims: 'The Eiffel Tower was built in 1776 by Gustave Moreau and stands 450 meters tall.'

## When to prefer this

Choose this endpoint when you need to automatically screen AI-generated text for hallucinations before presenting it to end users, when auditing LLM output quality in a pipeline, or when building a safety gate that flags fabricated facts. It is especially useful for RAG systems, chatbot guardrails, and LLM evaluation workflows where factual reliability is critical.

## Known failure modes

- Empty or null 'data' field returns an error or empty result
- Extremely long text may exceed processing limits
- Ambiguous or opinion-based content may produce false positives
- Network timeout for large payloads
- Payment failure (402) if USDC balance is insufficient

## 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 structured result indicating whether hallucinations were detected in the input text, along with flagged spans or claims that appear fabricated or unsupported, and likely a confidence or severity score for each detected issue.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "payload": {
   "type": "string"
  }
 }
}
```

## Response schema (JSON Schema)

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

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/hallucination-detector-mcp-22dc8c2e/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)