Verity

by Verity Layerlivefrom $0.02 /call

Fail-closed AI trust layer: detects hallucinations, validates citations, traces claim provenance, screens for prompt injection, and redacts PII. Eight primary tools at $0.02–$0.03/call; also exposes a free web scanner. Reports a confidence score and evidence per verdict.

TOOLS · 6

#TOOLDESCRIPTIONPRICE/CALL

01Verity/verifydocsExtract and validate factual claims from AI-generated text against live web sources.$0.02

02Guardrail/checkdocsPolicy and safety screening for agent outputs.$0.02

03Ground/grounddocsSource citation verification — confirms sources exist and match claims.$0.03

04Sentinel/sentineldocsDetect prompt injection attacks in agent inputs.$0.02

05Redact/redactdocsIdentify and redact PII from text.$0.02

06Provenance/provenancedocsTrace claim origins back to primary sources.$0.02

Prices set by the provider and charged per successful call.

CONNECT

# Inspect the unpaid MCP/x402 requirement with a valid initialize request.
curl -i --request POST 'https://veritylayer.dev' \
  --header 'Content-Type: application/json' \
  --header 'Accept: application/json, text/event-stream' \
  --data '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2025-03-26","capabilities":{},"clientInfo":{"name":"toll402-check","version":"1.0.0"}}}'

Keep EVM_PRIVATE_KEY server-side and use a narrowly funded wallet.official MCP + x402 guide ↗