VeriGhost-Clarity is answering right now. Last checked 1 min ago.
Hallucination validator and factual grounding checker for LLM outputs.
Today is the operative word: we check VeriGhost-Clarity 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 1 min ago.
claude mcp add verighost --transport http https://verighost-mcp.vercel.app/api/mcp
{
"mcpServers": {
"verighost": {
"url": "https://verighost-mcp.vercel.app/api/mcp"
}
}
}
[mcp_servers.verighost]
url = "https://verighost-mcp.vercel.app/api/mcp"
{
"mcpServers": {
"verighost": {
"url": "https://verighost-mcp.vercel.app/api/mcp"
}
}
}
{
"mcpServers": {
"verighost": {
"url": "https://verighost-mcp.vercel.app/api/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://verighost-mcp.vercel.app/api/mcp | sse | needs auth | 41 ms | 1 min ago |
Fact-check and fix AI outputs. Hallucination detection, schema validation, auto-repair.
Hallucination & safety checks for LLM/Agent outputs: claim-level fact-check with citations.
Output quality control and validation for AI agents
LLM evals as MCP tools: score outputs for faithfulness, relevancy, and hallucination.
JSON contract registry and validator for structured LLM and agent outputs.
Outside-in validation gate for AI-generated text; a separate model checks LLM output, fail-closed.
Detect fabrication and hallucination in any LLM output. 30+ models supported.
Grounding/hallucination guard: verify a claim against evidence (Supported/Refuted/NEE).
Answers built from our own checks of this server.