LLMVerify

io.github.subodhkcv1.8.0Updated Oct 9, 2026

Local-first MCP server for LLM output verification — risk signals, injection and PII checks.

VerifiedSTDIODesktop onlyAI & ML Security & Monitoring

Overview

AI-generated overview

Local MCP server that checks LLM outputs for hallucination risk, prompt injection, and PII, and can redact sensitive data.

What it does: LLMVerify exposes a local verification engine to MCP-compatible agents over stdio. Its six tools are verify_llm_content, assess_hallucination_risk, check_prompt_injection, check_pii, redact_pii, and get_llmverify_capabilities. Checks are deterministic and pattern-based, covering hallucination and consistency signals, injection and jailbreak patterns, and standard PII formats such as emails, phone numbers, SSNs, credit cards, and common API keys. Results include an explicit limitations or notChecked list.
When to use it: Use it when an assistant handles untrusted user input or model output and you want a local guardrail before content reaches users or logs. It suits triage of injection attempts, PII screening, and redaction, not ground-truth fact checking or approval decisions.
Requirements: Runs locally via npx from the npm package llmverify; the MCP command needs Node.js 20 or newer. No account or API key is required, and the free tier makes no network requests. Optional environment variables configure audit, baseline, log, and state directories, plus input/output size caps and a per-tool timeout.

Before you install

Detection is pattern-based: hallucination signals cannot prove a claim false, and obfuscated or encoded PII and novel injections may be missed. Redaction and verification results should not replace human review. The optional secret LLMVERIFY_AUDIT_HASH_KEY enables keyed content hashes in audit records; setting LLMVERIFY_AUDIT_NO_CONTENT_HASH disables content hashes. The separate local HTTP server has no authentication, so exposing it beyond localhost is risky.

Installation

In SourceWeft

Open LLMVerify in the dashboard and add it to a workspace.
Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

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.

[npm version] [CI] [License: MIT]

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

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

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

Function	One-liner	What it does
`verify(content)`	`await verify(aiResponse)`	Runs hallucination, consistency, safety, and CSM6 checks; returns a risk level and findings
`isInputSafe(input)`	`isInputSafe(userMessage)`	Blocks prompt injection, jailbreaks, and malicious input before it reaches the model
`redactPII(text)`	`redactPII(aiResponse)`	Masks emails, phones, SSNs, credit cards, and API keys
`containsPII(text)`	`containsPII(text)`	Returns true if PII is present
`detectAndRepairJson(...)`	`detectAndRepairJson(prompt, response)`	Detects and repairs broken JSON output
`monitorLLM(client)`	`monitorLLM(openaiClient)`	Wraps any LLM client; tracks latency, token drift, and behavioral changes
`sentinel.quick(...)`	`await sentinel.quick(client, model)`	Runs regression tests against your model before users see changes
`classify(...)`	`classify(prompt, response)`	Intent detection, hallucination signals, and instruction compliance
`auditLog(event)`	`auditLog({ ... })`	Appends a local, hash-only audit entry for SOC 2 / HIPAA / GDPR evidence
`run`, `prodVerify`, `ciVerify`	`await prodVerify(content)`	Preset pipelines for dev, prod, strict, fast, and CI use

Quick start (30 seconds)

javascript

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);

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);

Three lines of safety between your LLM and your users. No config file required. No API key required.

How it works

llmverify runs deterministic, pattern-based engines locally — no model calls, no network on the free tier. Same input plus same rules equals same result. Every result carries an explicit limitations array stating what was and was not checked, so you never mistake a clean score for a guarantee.

Framework alignment (baseline mapping only — not certification):

OWASP LLM Top 10
NIST AI RMF
EU AI Act
ISO 42001
CSM6 (HAIEC's 38-rule control set)

CLI

bash

# Verify a string from the terminal.npx llmverify verify "The capital of France is London."
# Start a local HTTP API for IDE / tool integration (localhost only by default).npx llmverify-serve --port=9009
# Expose to the network only on a trusted network. There is no auth on the API.npx llmverify-serve --host=0.0.0.0 --port=9009

# Verify a string from the terminal.npx llmverify verify "The capital of France is London."
# Start a local HTTP API for IDE / tool integration (localhost only by default).npx llmverify-serve --port=9009
# Expose to the network only on a trusted network. There is no auth on the API.npx llmverify-serve --host=0.0.0.0 --port=9009

The server binds to 127.0.0.1 by default, restricts CORS to localhost origins, and rate-limits clients (100 requests / 60s). It requires express (an optional dependency that installs by default).

MCP server

llmverify ships a built-in Model Context Protocol server — the same engine, exposed to MCP-compatible agents and IDEs over stdio:

jsonc

// MCP client config{  "mcpServers": {    "llmverify": {      "command": "npx",      "args": ["-y", "llmverify", "mcp"]    }  }}

// MCP client config{  "mcpServers": {    "llmverify": {      "command": "npx",      "args": ["-y", "llmverify", "mcp"]    }  }}

Six tools: verify_llm_content, assess_hallucination_risk, check_prompt_injection, check_pii, redact_pii, get_llmverify_capabilities. Stdio-only, zero outbound network, bounded inputs/outputs, PII-filtered responses, honest notChecked/audit semantics.

Requires Node.js ≥ 20 (the MCP SDK's floor; the rest of the package supports ≥ 18). The MCP SDK and zod are regular dependencies — the mcp command lazy-loads them so other commands pay no startup cost.

See docs/MCP.md for the full tool reference and security model.

Limitations

llmverify is a triage tool, not a truth oracle. Be honest with yourself about what it can and cannot do:

It cannot definitively prove hallucinations. Hallucination signals are pattern-based. "The capital of France is London" scores low because the text looks internally consistent. Ground-truth verification requires a source document you provide.
It does not replace human review. Use it to triage, not to approve.
PII detection is regex-based. It catches standard formats (emails, US phones, SSNs, credit cards, common API keys). It misses obfuscated, image-embedded, or encoded PII. Accuracy is roughly 90% for standard formats, lower for variations.
Prompt-injection detection is pattern-based. Novel or obfuscated injections can evade it.
Free tier is 100% local. ML-enhanced features require a paid tier and an explicit API key; the free tier never makes network requests and never sends data anywhere.

If a claim matters, verify it yourself. llmverify narrows the risk surface; it does not eliminate it.

Documentation

Part of HAIEC

llmverify is part of the HAIEC (Human AI Evidence Company) AI governance platform. Use it alongside the AI Security Scanner, the CI/CD pipeline integration, and Runtime Injection Testing.

Support

Issues: GitHub Issues
Docs: Full documentation

License

MIT — see LICENSE.

Recommendation (not legal advice): Run verify() on every model output that reaches a user, and isInputSafe() on every user input that reaches a model. Treat the risk level as a triage signal, not an approval.

Source: README.md at commit 2d130f6

Tools

Tool metadata has not been indexed yet.

Version history

v1.8.0LatestOct 9, 2026