AI model health monitor for LLM apps – runtime checks for drift, hallucination risk, latency, and JSON/format quality on any OpenAI, Anthropic, or local client.
Setup
Choose your client, copy the config, then fill in any required environment variables.
claude mcp add llmverify --env LLMVERIFY_AUDIT_HASH_KEY='<LLMVERIFY_AUDIT_HASH_KEY>' -- npx -y llmverify~/.codex/config.toml
[mcp_servers.llmverify]
command = "npx"
args = ["-y", "llmverify"]
env = { LLMVERIFY_AUDIT_HASH_KEY = "<LLMVERIFY_AUDIT_HASH_KEY>" }
# codex mcp add llmverify --env LLMVERIFY_AUDIT_HASH_KEY='<LLMVERIFY_AUDIT_HASH_KEY>' -- npx -y llmverify~/.cursor/mcp.json
{
"mcpServers": {
"llmverify": {
"command": "npx",
"args": [
"-y",
"llmverify"
],
"env": {
"LLMVERIFY_AUDIT_HASH_KEY": "<LLMVERIFY_AUDIT_HASH_KEY>"
}
}
}
}.vscode/mcp.json
{
"servers": {
"llmverify": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"llmverify"
],
"env": {
"LLMVERIFY_AUDIT_HASH_KEY": "<LLMVERIFY_AUDIT_HASH_KEY>"
}
}
}
}~/.gemini/settings.json
{
"mcpServers": {
"llmverify": {
"command": "npx",
"args": [
"-y",
"llmverify"
],
"env": {
"LLMVERIFY_AUDIT_HASH_KEY": "<LLMVERIFY_AUDIT_HASH_KEY>"
}
}
}
}claude_desktop_config.json
{
"mcpServers": {
"llmverify": {
"command": "npx",
"args": [
"-y",
"llmverify"
],
"env": {
"LLMVERIFY_AUDIT_HASH_KEY": "<LLMVERIFY_AUDIT_HASH_KEY>"
}
}
}
}.trae/mcp.json
{
"mcpServers": {
"llmverify": {
"command": "npx",
"args": [
"-y",
"llmverify"
],
"env": {
"LLMVERIFY_AUDIT_HASH_KEY": "<LLMVERIFY_AUDIT_HASH_KEY>"
}
}
}
}Environment variables
LLMVERIFY_AUDIT_HASH_KEY
Replace the placeholders with your own credentials and keep them out of version control.