LLMVerify MCP server

llmverify

You shipped an AI feature. Your LLM hallucinated a citation, leaked a customer's email, and followed a prompt-injection buried in user input — on the same day. llmverify is the safety layer that sits between your LLM and your users.

Local-first verification, PII redaction, prompt-injection defense, and runtime monitoring for any LLM. One npm install. Zero telemetry. No API keys on the free tier.

Last Updated: August 21, 2026 Version: 1.7.0 Node: >= 18.0.0 License: MIT

Links

• Product page: haiec.com/llmverify
• npm: npmjs.com/package/llmverify
• GitHub: github.com/subodhkc/llmverify-npm
• Python (placeholder): pypi.org/project/llmverify — namespace reservation, not a port of this package
• Author: Subodh Kc

The problem

You build with GPT-4, Claude, Gemini, or any LLM. The model:

• Hallucinates facts and citations that do not exist.
• Leaks PII — emails, phone numbers, SSNs, API keys in responses.
• Follows prompt injections — users trick it into ignoring your instructions.
• Returns broken JSON that crashes your parser.
• Drifts in quality over time, and nobody notices until a user complains.

You need a guardrail between the model and your users. That is llmverify.

Install

npm install llmverify

Everything runs locally. The free tier makes zero network requests and needs no API key. Free tier limit: 500 verification calls per day (tracked locally, never sent anywhere).

What you get

Quick start (30 seconds)

const { verify, isInputSafe, redactPII } = require('llmverify');

// 1. Block prompt injection before it reaches the model.
if (!isInputSafe(userMessage)) {
  return { error: 'Invalid input detected' };
}

// 2. Verify the model's output.
const aiResponse = await yourLLM.generate(userMessage);
const result = await verify(aiResponse);

if (result.risk.level === 'critical') {
  return { error: 'Response failed safety check' };
}

// 3. Strip PII before the response reaches a user or a log.
const { redacted } = redactPII(aiResponse);
console.log(redacted);

Shortened. The full README is on GitHub.