What it does
POST content with a claim_type and receive a validation verdict, a confidence score, and a signed certificate of the audit result. Use before consuming third-party API output or LLM-generated facts — verify integrity before injecting into your agent's reasoning loop. The signed certificate lets downstream consumers verify the audit independently. Pairs well with SchemaGate (structural validation) and PromptGuard (injection detection) for end-to-end response safety.
When to use it
- Validate facts in LLM-generated content before publishing
- Audit third-party API responses before consuming downstream
- Gate tool-call outputs against factual claims in a research workflow
- Generate signed audit certificates for compliance trails
Request schema
{
"content": "Australia's capital is Sydney.",
"claim_type": "factual"
} Response schema
{
"verdict": "invalid",
"confidence": 0.97,
"reasoning": "Australia's capital is Canberra, not Sydney.",
"certificate": "cert_8a3f...signed",
"payment_hash": "0x..."
} Code example — TypeScript via MCP
Install the MCP server once; all 22 services become tool calls.
// Configure @melis-ai/x402-tools-mcp in your MCP client
// Then call the tool:
const result = await mcpClient.callTool("xaudit", {
"content": "Australia's capital is Sydney.",
"claim_type": "factual"
});
console.log(result);
// ["verdict","confidence","reasoning","certificate","payment_h... → MCP setup guide Code example — Python via direct HTTP
import requests
# x402 payment header must be set by your wallet client
# See x402.org for client libraries
headers = {
"Content-Type": "application/json",
"x-payment": "<signed-x402-payment-header>",
}
resp = requests.post(
"https://xaudit.melis.ai/validate",
json={
"content": "Australia's capital is Sydney.",
"claim_type": "factual"
},
headers=headers,
)
print(resp.json()) Code example — curl with internal key bypass
For testing with an issued internal key (skips x402 payment flow):
curl -X POST https://xaudit.melis.ai/validate \
-H "Content-Type: application/json" \
-H "x-internal-key: YOUR_KEY" \
-d '{"content":"Australia's capital is Sydney.","claim_type":"factual"}' How is this different from alternatives?
xAudit vs SchemaGate
SchemaGate validates structure (does the JSON match the schema?). xAudit validates content (is the claim accurate?). They target different failure modes — use both for a full response-safety pipeline.
xAudit vs PromptGuard
PromptGuard checks input strings for injection signals. xAudit checks output content for factual integrity. Different layer of the safety stack.
FAQ
Does it work without an account?
Yes. x402 is account-less. Your agent's wallet signs the payment and retries automatically. No registration, no API key, no subscription.
What happens on failure?
Returns HTTP 400 if content is missing or claim_type is unrecognised. No settlement on any non-2xx response.
What is the rate limit?
None published.
Is this open-source?
The service code is closed-source for security reasons. The MCP wrapper that calls it is open-source and MIT-licensed: github.com/mizukaizen/x402-tools-mcp .
Who built this?
Part of the melis.ai agent infrastructure stack. Running on a dedicated Helsinki VPS since early 2026. Contact sean@melis.ai.