A standalone MCP server that validates model output against retrieved sources. It flags any claim, statistic, attribution, quote, or URL that cannot be traced back to a real source.
Verifies factual claims against live sources and returns a verdict, confidence score, and citations for any agent to use before stating uncertain facts.
Enables agents to verify claims with evidence-based truth scores and confidence levels by running a deterministic pipeline of evidence lanes and adversarial checks.
Extracts verifiable, decontextualized factual claims from text using a research-based four-stage pipeline (sentence splitting, selection, disambiguation, and decomposition). Integrates with MCP clients to enable claim extraction and verification workflows.
An MCP server that verifies whether a claim is actually supported by the source text at a given citation — independent of what the calling LLM asserts.