HallucC — Hallucination & Safety Guardian is answering right now. Last checked 8 min ago. Last commit 17 Sep 2026.
Hallucination & safety checks for LLM/Agent outputs: claim-level fact-check with citations.
Over the last week it answered 99.4% of our checks. We check every 15 minutes, so you hear about the next outage within the hour — not from your users.
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 8 min ago.
claude mcp add hallucc --transport http https://aihcc.cloud/mcp
{
"mcpServers": {
"hallucc": {
"url": "https://aihcc.cloud/mcp"
}
}
}
[mcp_servers.hallucc]
url = "https://aihcc.cloud/mcp"
{
"mcpServers": {
"hallucc": {
"url": "https://aihcc.cloud/mcp"
}
}
}
{
"mcpServers": {
"hallucc": {
"url": "https://aihcc.cloud/mcp"
}
}
}
This endpoint answered with an authorization challenge. The server is running, but it did not say what kind of credentials it expects.
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://aihcc.cloud/mcp | streamable-http | needs auth | 896 ms | 8 min ago |
Hallucination validator and factual grounding checker for LLM outputs.
Fact-check any claim with live web sources. Ed25519-signed receipts. Catches hallucinations.
Verified knowledge base for AI agents — stop hallucinations with certified facts.
Fact-check and fix AI outputs. Hallucination detection, schema validation, auto-repair.
Condition-aware ingredient and product checks for agents, with evidence tiers and citations.
LLM evals as MCP tools: score outputs for faithfulness, relevancy, and hallucination.
Living knowledge graph for your repo: query with citations, remember/link facts, fact-check claims.
Fabrication-free, DOI-backed citations for AI agents — real openAlex sources, never hallucinated.
Answers built from our own checks of this server.