Fidenta Verify is answering right now. Last checked 10 min ago. It exposes 5 tools.
Independent fact-checking for AI answers: a verdict and sources for every claim.
Today is the operative word: we check Fidenta Verify every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 10 min ago.
claude mcp add fidenta-verify --transport http https://verify.noevant.ai/mcp
https://verify.noevant.ai/mcp
[mcp_servers.fidenta-verify]
url = "https://verify.noevant.ai/mcp"
{
"mcpServers": {
"fidenta-verify": {
"url": "https://verify.noevant.ai/mcp"
}
}
}
{
"servers": {
"fidenta-verify": {
"type": "http",
"url": "https://verify.noevant.ai/mcp"
}
}
}
Read directly from the server with tools/list, grouped by what they act on.
If a tool disappears, we record the date.
estimate_claims
recall_claim
top_up
check_usage
verify_claims
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://verify.noevant.ai/mcp | streamable-http | answering | 105 ms | 10 min ago |
Verifiable fact-checking: verdict, confidence, sources, and a tamper-evident certificate.
Check the factual claims in a draft or an answer: a quick verdict, or a deep check with sources.
Independent verifier for AI agents: checks agent claims and doc promises against the code.
Fact-check AI answers with cited sources. Pay per call in USDC on Base via x402.
Real-time fact-checking MCP. Verifies claims against live sources with structured verdicts.
Independent trust scores, tool surfaces and change history for MCP servers.
Honest claim corroboration for AI agents: syndication-aware independent-source counting.
Every agent action watched, every money-moving one gated, every verdict independently verifiable.
Answers built from our own checks of this server.