LLMVerify
Local-first MCP server for LLM output verification — risk signals, injection and PII checks.
Servidor MCP · de subodhkc
Resumo
LLMVerify é um servidor MCP publicado por subodhkc. Marketplaces que lemos e que o listam: 1 (Official MCP Registry). Vimos pela primeira vez em 2026-10-11 e não registramos mudanças desde então. Conforme nossa passagem pelos marketplaces em 2026-10-12.
O que pede
- Roda na sua máquina
- Segredos: 1
- Configurações: 11
Exige: LLMVERIFY_AUDIT_HASH_KEY (secreta)
O que declara, pede e executa, por completo
Instale apenas plugins de desenvolvedores em quem você confia. Mostramos o que os marketplaces publicam e não testamos plugins.
Funciona com
- Claude Code
- Codex
- Cursor
- VS Code
- Copilot CLI
Pelos marketplaces que o listam e pelo transporte MCP que declara, conforme cada cliente documenta. Não testamos plugins.
Conectar
Comandos e configurações gerados apenas a partir do que os marketplaces declaram. Não os executamos por você e não testamos plugins.
Como servidor MCP local: pacote npm
Gerado a partir do que Official MCP Registry declara.
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>"
}
}
}
}Substitua os valores entre sinais de menor e maior pelos seus. Mostramos os nomes das configurações, nunca valores.
Configurações opcionais que também indica: 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.
Não guardamos argumentos de inicialização. Se o servidor precisar de algum, a própria documentação dele os indica.
Onde está publicado
| Marketplace | Status | Versão | Números | Verificado | Visto pela primeira vez |
|---|---|---|---|---|---|
| Official MCP Registry (Abrir o registro) | Listado | 1.8.0 | Forks (GitHub): 17 Estrelas (GitHub): 18 |
Sem marcação |
Cada número é do próprio marketplace e nunca é somado entre marketplaces. Um marketplace que não publica números não mostra nenhum: sem número não é zero.
O que mudou
Nada mudou neste plugin desde que começamos a acompanhá-lo.
Plugins semelhantes
Produtos cujos próprios nomes, descrições, ferramentas e skills são os mais próximos deste pelo significado, em todos os marketplaces que lemos. A proximidade é ordenada apenas dentro desta lista.
-
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.
Plugins semelhantes por marketplace
A mesma pergunta feita a cada marketplace separadamente: existe lá um equivalente deste plugin?
Listado em 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.
Listado em 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…
Listado em 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.
Listado em 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…
Listado em 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.
Listado em 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.
Listado em 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…
Listado em 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.
Listado em 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.
Listado em 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.
Encontrados pelo significado, não por código ou repositório em comum: plugins semelhantes continuam sendo produtos distintos, e isto não é uma avaliação nem uma recomendação.
Este plugin é seu?
Adicione-o aos seus projetos e prove que o mantém com um arquivo no repositório, um arquivo no seu domínio ou um registro DNS. Você recebe alertas quando um marketplace o publica, o remove, muda a marca de verificado ou o que ele pede, e o endpoint remoto passa a ser monitorado como um serviço web.
Dados de Official MCP Registry. Os números vêm das nossas próprias passagens regulares pelos marketplaces, última leitura em . Não publicamos dados de contato dos editores de plugins.