eleata Claim Verifier runs on your own machine — the client starts it, so there is no endpoint to ping. 34 installs a week from npm. Last commit 30 Jun 2026.
Grounding/hallucination guard: verify a claim against evidence (Supported/Refuted/NEE).
Today is the operative word: we check eleata Claim Verifier every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add eleata-verify-mcp -- npx -y eleata-verify-mcp
{
"mcpServers": {
"eleata-verify-mcp": {
"args": [
"-y",
"eleata-verify-mcp"
],
"command": "npx"
}
}
}
[mcp_servers.eleata-verify-mcp]
command = "npx"
args = ["-y", "eleata-verify-mcp"]
{
"mcpServers": {
"eleata-verify-mcp": {
"args": [
"-y",
"eleata-verify-mcp"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"eleata-verify-mcp": {
"args": [
"-y",
"eleata-verify-mcp"
],
"command": "npx"
}
}
}
This one needs environment variables set before it will start:
EVERIFY_API_KEY (API key for the eleata Claim Verifier (paid Bearer or RapidAPI key)).
The author declared them in the registry entry; get the values from the project itself.
Execution-grounded verification for AI coding agents on Windows: evidence, not agent claims.
Verify academic citations against real databases. Catches hallucinated references, exports BibTeX.
Verify legal case citations against real court records; flag fake/hallucinated cites.
Hallucination validator and factual grounding checker for LLM outputs.
Verify a vuln report's file/line/function claims against a real GitHub repo.
Force evidence-gated, tiered claim reporting (FACT/INFERENCE/SPECULATION). No-LLM.
Ed25519-signed verdicts resolved against real ground truth. Free claim/verify; paid bonded dispute.
Verify AI agent claims vs reality: inline grounding-check + swallowed-exception + transcript review.
Answers built from our own checks of this server.