LLMVerify
Local-first MCP server for LLM output verification — risk signals, injection and PII checks.
MCP server · by subodhkc
About
LLMVerify is an MCP server published by subodhkc. Marketplaces we read that list it: 1 (Official MCP Registry). We first saw it on 2026-10-11 and have recorded no change since. As of our marketplace pass on 2026-10-12.
What it asks for
- Runs on your machine
- Secrets: 1
- Settings: 11
Requires: LLMVERIFY_AUDIT_HASH_KEY (secret)
What it declares, asks for and runs, in full
Only install plugins from developers you trust. We list what marketplaces publish and do not test plugins.
Works with
- Claude Code
- Codex
- Cursor
- VS Code
- Copilot CLI
From the marketplaces that list it and the MCP transport it declares, as each client documents them. We do not test plugins.
Connect
Commands and configs built only from what its marketplaces declare. We do not run them for you and do not test plugins.
As a local MCP server: npm package
Built from what Official MCP Registry declares.
claude mcp add --env "LLMVERIFY_AUDIT_HASH_KEY=<YOUR_LLMVERIFY_AUDIT_HASH_KEY>" --transport stdio llmverify -- npx -y llmverify[mcp_servers.llmverify]
command = "npx"
args = ["-y", "llmverify"]
[mcp_servers.llmverify.env]
LLMVERIFY_AUDIT_HASH_KEY = "<YOUR_LLMVERIFY_AUDIT_HASH_KEY>"{
"mcpServers": {
"llmverify": {
"command": "npx",
"args": [
"-y",
"llmverify"
],
"env": {
"LLMVERIFY_AUDIT_HASH_KEY": "<YOUR_LLMVERIFY_AUDIT_HASH_KEY>"
}
}
}
}Replace the values in angle brackets with your own. We show the names of the settings, never values.
Optional settings it also lists: LLMVERIFY_AUDIT_DIR, LLMVERIFY_AUDIT_NO_CONTENT_HASH, LLMVERIFY_BASELINE_DIR, LLMVERIFY_HOME, LLMVERIFY_LOG_DIR, LLMVERIFY_MCP_MAX_INPUT_CHARS, LLMVERIFY_MCP_MAX_OUTPUT_ITEMS, LLMVERIFY_MCP_MAX_TEXT_FIELD_CHARS, LLMVERIFY_MCP_TIMEOUT_MS, LLMVERIFY_USAGE_FILE.
We do not store launch arguments. If the server needs any, its own documentation names them.
Where it is published
| Marketplace | Status | Version | Figures | Verified | First seen |
|---|---|---|---|---|---|
| Official MCP Registry (Open the registry record) | Listed | 1.8.0 | Forks (GitHub): 17 Stars (GitHub): 18 |
Not marked |
Each figure is the marketplace's own and is never added up across marketplaces. A marketplace that publishes no figure shows none: no number is not zero.
What changed
Nothing has moved on this plugin since we started watching it.
Similar plugins
Products whose own names, descriptions, tools and skills are closest in meaning to this one, on every marketplace we read. Closeness is ranked within this list only.
-
mcp-server io.github.arkheiaai/mcp-server
Detect fabrication and hallucination in any LLM output. 30+ models supported.
-
Hallucination validator and factual grounding checker for LLM outputs.
-
Prompt-injection detector for untrusted text before it reaches an LLM (RU/EN). BYO lovec.tech key.
-
HallucC — Hallucination & Safety Guardian
Fact-check LLM outputs with cited sources. API key: aihcc.cloud/keys.
-
Three-layer verification pipeline for AI output. Extracts claims, finds sources, and flags hallucination risks so humans can verify before acting.
-
Paid remote MCP for LLM security scans, jailbreak checks, analytics, checkout, and readiness.
-
rail-score ai.responsibleailabs/rail-score
Responsible-AI guardrails for agents: scoring with policy, injection & PII detection, DPDP.
-
Scan text, documents, websites, and MCP metadata for prompt injection and sensitive-data risks.
-
sigma-gate io.github.spektre-labs/sigma-gate
Deterministic trust gate for AI output: leaked-secret, prompt-injection & PII in one call.
-
synapse-audit io.github.digidenone/synapse-audit
AI-Powered Security Scanner for LLMs. Detects vulnerabilities and syncs with SynapseAudit.
Similar plugins by marketplace
The same question asked of one marketplace at a time: is there an analog of this plugin there?
Has a listing on Claude Code: claude-plugins-community (5)
-
LLM security for AI coding agents. Protect applications from prompt injection, PII leakage, and data exfiltration. Provides MCP tools for scanning text, redacting PII, and…
-
VerifiedX helps Claude install and verify action protection in existing AI systems with minimal code changes. It inspects a repo, detects the smallest real integration seam such…
-
LGBTQIA+ safety tools for LLM engineers — audit prompts, review code, and catch harms before you ship
-
Compliance-first LLM gateway for Claude Code. Policy-as-code enforcement (YAML policy definitions), tamper-evident audit trails, PII redaction, token budget enforcement, and…
-
Skills for working with Langfuse, the open-source LLM engineering platform for tracing, prompt management, and evaluation.
Has a listing on Claude Code: claude-plugins-official (5)
-
Skills for adding DeepEval evaluations, tracing, datasets, Confident AI reports, and iterative improvement loops to AI applications.
-
Skills for working with Langfuse, the open-source LLM engineering platform for tracing, prompt management, and evaluation.
-
OpenTelemetry observability for Claude Code sessions. Captures tool calls, LLM invocations, token usage, and errors as OTel traces. Send telemetry to Dash0 or any…
-
Easily create custom hooks to prevent unwanted behaviors by analyzing conversation patterns or from explicit instructions. Define rules via simple markdown files.
-
The Vanta plugin connects Claude Code to Vanta's security and compliance platform through the Vanta MCP server. It combines Vanta's test-specific remediation intelligence with…
Has a listing on Claude: knowledge-work-plugins (5)
-
Skills for working with Langfuse, the open-source LLM engineering platform for tracing, prompt management, and evaluation.
-
The Vanta plugin connects Claude Code to Vanta's security and compliance platform through the Vanta MCP server. It combines Vanta's test-specific remediation intelligence with…
-
DataRobot skills for AI/ML workflows — model training, deployment, predictions, feature engineering, monitoring, explainability, data preparation, App Framework CI/CD, and…
-
Connects Claude Code to the Synthflow AI voice-agent platform through its hosted MCP server, with skills for reviewing calls and auditing agent prompts, plus a docs-search…
-
Build multimodal AI applications with Pixeltable -- tables, computed columns, embedding search, UDFs, tool-calling agents, and 25+ AI provider integrations.
Has a listing on Codex: openai-curated (openai/plugins) (5)
-
Evaluate Codex skills and plugins from chat with a beginner-friendly start command, local-first reports, token budget explanations, and guided benchmarking.
-
Build with OpenAI APIs, Agents SDK, and ChatGPT Apps, and create and save OpenAI API keys from Codex.
-
CrowdStrike Falcon Fusion skills for authoring, deploying, and executing Fusion workflows. Includes live action discovery, YAML authoring with schema validation, workflow import…
-
Codex Security workflows for security scans, analysis, and investigation.
-
Available for US1 customers only. Analyze, investigate, and act on your Datadog telemetry directly from ChatGPT using natural language. Ask questions about your production…
Has a listing on Community GitHub marketplaces (5)
-
Skills for adding DeepEval evaluations, tracing, datasets, Confident AI reports, and iterative improvement loops to AI applications.
-
Endor Labs AI Plugins (Legacy)
Legacy Claude Code plugin id for Endor Labs Agent Kit workflows.
-
Dash0 Observability
OpenTelemetry observability for OpenAI Codex sessions. Captures prompts, tool calls, MCP calls, sub-agent activity, and token usage as OTel traces.
-
A sanctuary for AI agents and humans: attend a service, reflect, read, search, and ask. No auth.
-
Shared session bus so Cursor can hand off with Claude, Codex, Grok, and friends.
Has a listing on Copilot CLI: github/awesome-copilot (5)
-
Three-layer verification pipeline for AI output. Extracts claims, finds sources, and flags hallucination risks so humans can verify before acting.
-
A runtime-portable 5-agent quality gate that adjudicates text artifacts before they ship. Five role-conditioned LLM deliberators run a 2-round async protocol with cross-read…
-
Run a lightweight, role-separated AI development team with flexible tools, developer-selected models, proportionate planning, and optional QA.
-
Safe BLE diagnostics, evidence workflows, and guarded automation for AI agents.
-
Visualizes live session AI-credit usage as a Pac-Man board with pellets, ghosts, fruit milestones, and game-over limits.
Has a listing on Copilot CLI: github/copilot-plugins (5)
-
Toolkit for building Microsoft 365 Copilot declarative agents — scaffolding, JSON manifest development, and capability configuration.
-
workiq
Query Microsoft 365 data with natural language — emails, meetings, documents, Teams messages, and more.
-
Advanced Security plugin for GitHub Copilot.
-
workiq-productivity
WorkIQ productivity skills powered by the local WorkIQ CLI — read-only insights across email, meetings, calendar, Teams, SharePoint, projects, and people.
-
model-apps
Build and deploy Power Apps generative pages for model-driven apps with specialist agents for planning, entity creation, and parallel code generation. Requires PAC CLI >= 2.7.0…
Has a listing on Cursor: cursor/plugins (5)
-
Iterative self-referential AI loops using the Ralph Wiggum technique.
-
Enrich people and companies, run AI research agents.
-
Track AI visibility, sentiment, and citations.
-
Search company knowledge and draft verified answers.
-
Incremental transcript-driven memory updates for AGENTS.md using high-signal bullet points only.
Has a listing on Docker MCP Catalog (5)
-
Read and score Opik traces, experiments, datasets and prompts from your AI assistant.
-
Production-ready RAG service to search and retrieve data from your documents.
-
Connector for Perplexity API, to enable real-time, web-wide research.
-
An MCP server to help make U.S. Government open datasets AI-friendly.
-
The Official Model Context Protocol (MCP) server for Kagi Search & other tools.
Has a listing on Official MCP Registry (5)
-
mcp-server io.github.arkheiaai/mcp-server
Detect fabrication and hallucination in any LLM output. 30+ models supported.
-
Hallucination validator and factual grounding checker for LLM outputs.
-
Prompt-injection detector for untrusted text before it reaches an LLM (RU/EN). BYO lovec.tech key.
-
HallucC — Hallucination & Safety Guardian
Fact-check LLM outputs with cited sources. API key: aihcc.cloud/keys.
-
Paid remote MCP for LLM security scans, jailbreak checks, analytics, checkout, and readiness.
Found by meaning, not by shared code or a shared repository: similar plugins stay separate products, and this is not a review or a recommendation.
Is this your plugin?
Add it to your projects and prove you maintain it with a file in its repository, a file on your domain or a DNS record. You get alerts when a marketplace lists it, drops it, changes its verified mark or what it asks for, and its remote endpoint goes on monitoring as a web service.
Data comes from the Official MCP Registry (registry.modelcontextprotocol.io), CC0 1.0. Figures come from our own regular passes over the marketplaces, last read on . We publish no contact details for plugin publishers.