LLMVerify — Claude Code MCP server: what it does, how to install
Local guardrail server that screens model responses for prompt injections, leaked personal data, and hallucination risks before they reach users.
claude mcp add --env LLMVERIFY_MCP_MAX_INPUT_CHARS=<LLMVERIFY_MCP_MAX_INPUT_CHARS> --env LLMVERIFY_MCP_TIMEOUT_MS=<LLMVERIFY_MCP_TIMEOUT_MS> --env LLMVERIFY_MCP_MAX_OUTPUT_ITEMS=<LLMVERIFY_MCP_MAX_OUTPUT_ITEMS> --env LLMVERIFY_MCP_MAX_TEXT_FIELD_CHARS=<LLMVERIFY_MCP_MAX_TEXT_FIELD_CHARS> --env LLMVERIFY_HOME=<LLMVERIFY_HOME> --transport stdio llmverify -- npx -y llmverifyWhat LLMVerify does
LLMVerify acts as a safety layer between your model and downstream consumers. It runs locally over stdio without external network calls or cloud API keys. The server exposes six tools: verify_llm_content, assess_hallucination_risk, check_prompt_injection, check_pii, redact_pii, and get_llmverify_capabilities.
Inspection relies on deterministic pattern matching and regular expressions. The engine flags standard formats of emails, phone numbers, payment cards, and known API keys. Because it relies on static rules rather than external fact-checking models, obfuscated attacks or novel injections can evade detection. Starting the MCP server requires Node.js version 20 or higher.
What it helps with
- detect and redact personal data like emails or API keys in model outputs
- block prompt injections and malicious inputs before processing
- evaluate structural hallucination risks within generated text
- inspect model outputs locally without sending data over the network
Example prompts for the agent
- Use LLMVerify to check this generated text for sensitive personal data
- Assess the prompt injection risk for the input stored in
query.txt - Redact all detected phone numbers and credentials from the response
How to install LLMVerify
Platform CLI
claude mcp add --env LLMVERIFY_MCP_MAX_INPUT_CHARS=<LLMVERIFY_MCP_MAX_INPUT_CHARS> --env LLMVERIFY_MCP_TIMEOUT_MS=<LLMVERIFY_MCP_TIMEOUT_MS> --env LLMVERIFY_MCP_MAX_OUTPUT_ITEMS=<LLMVERIFY_MCP_MAX_OUTPUT_ITEMS> --env LLMVERIFY_MCP_MAX_TEXT_FIELD_CHARS=<LLMVERIFY_MCP_MAX_TEXT_FIELD_CHARS> --env LLMVERIFY_HOME=<LLMVERIFY_HOME> --transport stdio llmverify -- npx -y llmverifyReplace <…> with your own values. 6 more environment variables are in the server README
Platform CLI
codex mcp add llmverify --env LLMVERIFY_MCP_MAX_INPUT_CHARS=<LLMVERIFY_MCP_MAX_INPUT_CHARS> --env LLMVERIFY_MCP_TIMEOUT_MS=<LLMVERIFY_MCP_TIMEOUT_MS> --env LLMVERIFY_MCP_MAX_OUTPUT_ITEMS=<LLMVERIFY_MCP_MAX_OUTPUT_ITEMS> --env LLMVERIFY_MCP_MAX_TEXT_FIELD_CHARS=<LLMVERIFY_MCP_MAX_TEXT_FIELD_CHARS> --env LLMVERIFY_HOME=<LLMVERIFY_HOME> -- npx -y llmverifyReplace <…> with your own values. 6 more environment variables are in the server README
Config file
{
"mcpServers": {
"llmverify": {
"command": "npx",
"args": [
"-y",
"llmverify"
],
"env": {
"LLMVERIFY_MCP_MAX_INPUT_CHARS": "<LLMVERIFY_MCP_MAX_INPUT_CHARS>",
"LLMVERIFY_MCP_TIMEOUT_MS": "<LLMVERIFY_MCP_TIMEOUT_MS>",
"LLMVERIFY_MCP_MAX_OUTPUT_ITEMS": "<LLMVERIFY_MCP_MAX_OUTPUT_ITEMS>",
"LLMVERIFY_MCP_MAX_TEXT_FIELD_CHARS": "<LLMVERIFY_MCP_MAX_TEXT_FIELD_CHARS>",
"LLMVERIFY_HOME": "<LLMVERIFY_HOME>"
}
}
}
}Replace <…> with your own values. 6 more environment variables are in the server README
Config file
{
"servers": {
"llmverify": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"llmverify"
],
"env": {
"LLMVERIFY_MCP_MAX_INPUT_CHARS": "<LLMVERIFY_MCP_MAX_INPUT_CHARS>",
"LLMVERIFY_MCP_TIMEOUT_MS": "<LLMVERIFY_MCP_TIMEOUT_MS>",
"LLMVERIFY_MCP_MAX_OUTPUT_ITEMS": "<LLMVERIFY_MCP_MAX_OUTPUT_ITEMS>",
"LLMVERIFY_MCP_MAX_TEXT_FIELD_CHARS": "<LLMVERIFY_MCP_MAX_TEXT_FIELD_CHARS>",
"LLMVERIFY_HOME": "<LLMVERIFY_HOME>"
}
}
}
}Replace <…> with your own values. 6 more environment variables are in the server README
Platform CLI
gemini mcp add -e LLMVERIFY_MCP_MAX_INPUT_CHARS=<LLMVERIFY_MCP_MAX_INPUT_CHARS> -e LLMVERIFY_MCP_TIMEOUT_MS=<LLMVERIFY_MCP_TIMEOUT_MS> -e LLMVERIFY_MCP_MAX_OUTPUT_ITEMS=<LLMVERIFY_MCP_MAX_OUTPUT_ITEMS> -e LLMVERIFY_MCP_MAX_TEXT_FIELD_CHARS=<LLMVERIFY_MCP_MAX_TEXT_FIELD_CHARS> -e LLMVERIFY_HOME=<LLMVERIFY_HOME> llmverify npx -y llmverifyReplace <…> with your own values. 6 more environment variables are in the server README
Step by step, with commands for each platform: How to add an MCP server to Claude Code, Codex, Cursor, VS Code, Gemini CLI and more
Questions about LLMVerify
How do I install LLMVerify in Claude Code?
Run claude mcp add llmverify -e LLMVERIFY_AUDIT_HASH_KEY=<LLMVERIFY_AUDIT_HASH_KEY> -- npx -y llmverify. Ensure your environment has Node.js 20 or higher.
What does LLMVerify do?
It gives coding agents local tools to detect sensitive data, block prompt injection patterns, and calculate initial hallucination risk scores.
Does the free version make external network calls?
No, all rule evaluation happens on your local machine with zero telemetry. The free tier includes 500 daily checks tracked locally.
