AgentGuard
Local spend caps, kill-switch blocking and Ed25519-signed receipts for AI agent tool calls.
Servidor MCP · de MerchantGuard
Resumo
AgentGuard é um servidor MCP publicado por MerchantGuard. 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 2026-10-13.
O que pede
- Roda na sua máquina
- Segredos: 1
- Configurações: 21
Exige: AGENTGUARD_LICENSE_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.
Pacote
npm @agentguard-run/mcp (@agentguard-run/mcp no npm)
- Downloads do npm por semana: 60 (2026-10-12)
- Downloads do npm por mês: 689 (2026-10-12)
- Última versão no npm: 0.3.1, publicada em 2026-09-21
- A versão declarada 0.3.1 não consta no npm
Os dados do npm vêm do registro público do npm (registry.npmjs.org, api.npmjs.org). Cada número é do próprio registro e nunca é somado a outro. Um registro que não publica um número não mostra nenhum: sem número não é zero.
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 "AGENTGUARD_LICENSE_KEY=<YOUR_AGENTGUARD_LICENSE_KEY>" --transport stdio agentguard -- npx -y @agentguard-run/mcp[mcp_servers.agentguard]
command = "npx"
args = ["-y", "@agentguard-run/mcp"]
[mcp_servers.agentguard.env]
AGENTGUARD_LICENSE_KEY = "<YOUR_AGENTGUARD_LICENSE_KEY>"{
"mcpServers": {
"agentguard": {
"command": "npx",
"args": [
"-y",
"@agentguard-run/mcp"
],
"env": {
"AGENTGUARD_LICENSE_KEY": "<YOUR_AGENTGUARD_LICENSE_KEY>"
}
}
}
}Substitua os valores entre sinais de menor e maior pelos seus. Mostramos os nomes das configurações, nunca valores.
Configurações opcionais que também indica: AGENTGUARD_ACTOR_DIGEST, AGENTGUARD_ANONYMOUS_INSTALL_ID, AGENTGUARD_HOME, AGENTGUARD_INSTALL_ID, AGENTGUARD_LICENSE_ENDPOINT, AGENTGUARD_LOCK_COST_OVERRIDES, AGENTGUARD_MCP_DAILY_CAP_CENTS, AGENTGUARD_MCP_DISABLE_COST_OVERRIDE, AGENTGUARD_MCP_LEDGER, AGENTGUARD_MCP_PER_CALL_CAP_CENTS, AGENTGUARD_MCP_TENANT, AGENTGUARD_NO_BEACON, AGENTGUARD_TELEMETRY, BUILDKITE, CI, CIRCLECI, GITHUB_ACTIONS, GITLAB_CI, NETLIFY, VERCEL.
Onde está publicado
| Marketplace | Status | Versão | Números | Verificado | Visto pela primeira vez |
|---|---|---|---|---|---|
| Official MCP Registry (Abrir o registro) | Listado | 0.3.1 | Downloads por mês (npm): 689 Downloads por semana (npm): 60 Forks (GitHub): 0 Estrelas (GitHub): 0 |
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.
-
figuard-mcp io.github.figuard/figuard-mcp
Pre-flight spend authorization for AI agents. Set a budget, enforce limits, audit every decision.
-
agents com.obsmetrics.paygent/agents
Pay-per-call safety guards for AI agents: injection, tool-call, signing, secret, x402-trust.
-
agentpay-sentinel-mcp io.github.Rumblingb/agentpay-sentinel-mcp
Security guardrails for AI agent payments
-
Smart contract security for AI agents — verify, monitor, freeze, x402 payments
-
mandateguard io.github.ezequiellich44-cmd/mandateguard
Deterministic payment policy guardrail for AI agents - budgets, allowlists, signed mandates.
-
Meter, cap, and block AI agent spend before the provider is charged.
-
12-layer security configs for AI coding agents. Autonomous purchase via x402 (USDC on Base).
-
agentic-wallet-guardian-v3 io.github.rudimentall1/agentic-wallet-guardian-v3
Explainable ALLOW/WARN/BLOCK risk decisions for AI agent actions before execution, signed as OAA.
-
Authorization layer between AI agents and money: ALLOW/APPROVAL/DENY, budgets, audit.
-
Gate an AI agent's destructive actions behind human approval, with a tamper-evident log.
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)
-
MCP security gateway that wraps any MCP server with per-tool policies, Ed25519-signed decision receipts, and human approval gates. Shadow mode (default) logs every tool call…
-
Real-time security filter for MCP tool communications. Works as a Claude Code hook to inspect all data sent to and received from MCP servers. Detects prompt injection, API key…
-
Deterministic IAM control plane for AI agents. Translates natural language intent into minimal-scope Ed25519-signed envelopes. You bring your own data plane. Carryall governs…
-
Identity, credential vault, and audit security for AI agents. ClawLock gives every AI agent its own Ed25519 cryptographic identity, stores API keys in an AES-256-GCM encrypted…
-
Sovereignty infrastructure for AI agents. Gives your agent encrypted state (AES-256-GCM), self-custodied identity (Ed25519), selective disclosure (Pedersen commitments, Schnorr…
Listado em Claude Code: claude-plugins-official (5)
-
mcp-server io.github.cap-js/mcp-server
Model Context Protocol (MCP) server for AI-assisted development of CAP applications.
-
Set up endorctl and use Endor Labs to scan, prioritize, and fix security risks across your software supply chain
-
Build, deploy, and operate AI agents on AWS. Skills for scaffolding agents with Amazon Bedrock AgentCore, connecting tools, memory, policies, evaluation, debugging, and production…
-
Manage Zscaler Zero Trust Exchange via 400+ tools — ZPA, ZIA, ZDX, ZCC, ZTW, ZMS, EASM, and more.
-
Dynatrace observability skills: DQL query patterns, application and infrastructure monitoring, log analysis, problem investigation, and incident response workflows, with the…
Listado em Claude: knowledge-work-plugins (5)
-
Hosted MCP server for AI-assisted Grafana Cloud observability — no local installation required.
-
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…
-
Figma design platform integration. Access design files, extract component information, read design tokens, and translate designs into code. Bridge the gap between design and…
-
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…
-
Skills for working with Langfuse, the open-source LLM engineering platform for tracing, prompt management, and evaluation.
Listado em Codex: openai-curated (openai/plugins) (5)
-
CrowdStrike Falcon Foundry development skills for building cybersecurity applications on the Falcon platform. Includes UI development, collections, functions, workflows, API…
-
Cloudflare platform plugin with curated skills for Workers, Wrangler, and Agents SDK plus the official Cloudflare API MCP server.
-
CrowdStrike Falcon Fusion skills for authoring, deploying, and executing Fusion workflows. Includes live action discovery, YAML authoring with schema validation, workflow import…
-
Build with OpenAI APIs, Agents SDK, and ChatGPT Apps, and create and save OpenAI API keys from Codex.
-
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)
-
Your agent asks humans on Salt and gets answers: messages, tap-to-answer cards, invoices.
-
agentforge io.github.acarchidi/agentforge
DeFi safety layer for AI agents: wallet safety, token risk, tx decode/simulate. 20 tools.
-
4da-mcp-server io.github.4DA-Systems/4da-mcp-server
Upgrade intelligence for AI agents: what an upgrade changes, where it touches your code, CVE scans.
-
Build, deploy, and operate AI agents on AWS. Skills for scaffolding agents with Amazon Bedrock AgentCore, connecting tools, memory, policies, evaluation, debugging, and production…
-
agents-party io.github.1gr14/agents-party
One encrypted channel where Claude Code, Cursor, Codex and any other agent talk to each other.
Listado em Copilot CLI: github/awesome-copilot (5)
-
Safe BLE diagnostics, evidence workflows, and guarded automation for AI agents.
-
Skills and interactive Copilot canvas for designing, configuring, testing and deploying agents to Microsoft Foundry.
-
foundry-hosted-agent-copilotkit
Build CopilotKit + AG-UI web apps on Microsoft Foundry hosted agents (Microsoft Agent Framework): wiring, native Foundry primitives, human-in-the-loop approvals, azd deploy, and…
-
Complete toolkit for building Model Context Protocol (MCP) servers in Go using the official github.com/modelcontextprotocol/go-sdk. Includes instructions for best practices, a…
-
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.
-
Advanced Security plugin for GitHub Copilot.
-
mcp-apps
Generate MCP App widgets for MCP tools. Produces self-contained HTML widgets using the MCP Apps protocol.
-
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…
-
Build Power Apps Canvas Apps using the Canvas Authoring MCP server.
Listado em Cursor: cursor/plugins (5)
-
Fan large tasks out across parallel cloud agents with planners, workers, verifiers, and structured handoffs.
-
CLI-backed repo compatibility scans plus agents that audit startup, validation, and docs against reality.
-
Build apps, scripts, and automations with the TypeScript SDK.
-
Scaffold and validate new agent plugins.
-
Patterns for designing CLIs that coding agents can run reliably: flags, help with examples, pipelines, errors, idempotency, dry-run.
Listado em Docker MCP Catalog (5)
-
Give your AI agents trusted access to the full Postman platform.
-
Discover and connect to a curated marketplace of MCP servers for extending AI agent capabilities.
-
Wayfound’s MCP server allows business users to govern, supervise, and improve AI Agents.
-
A unified MCP proxy that aggregates multiple MCP servers into one interface, enabling seamless tool discovery and management across all your AI interactions. Manage all your MCP…
-
A universal MCP (Model Context Protocol) server to integrate any API with Claude Desktop using only Docker configurations.
Listado em Official MCP Registry (5)
-
figuard-mcp io.github.figuard/figuard-mcp
Pre-flight spend authorization for AI agents. Set a budget, enforce limits, audit every decision.
-
agents com.obsmetrics.paygent/agents
Pay-per-call safety guards for AI agents: injection, tool-call, signing, secret, x402-trust.
-
agentpay-sentinel-mcp io.github.Rumblingb/agentpay-sentinel-mcp
Security guardrails for AI agent payments
-
Smart contract security for AI agents — verify, monitor, freeze, x402 payments
-
mandateguard io.github.ezequiellich44-cmd/mandateguard
Deterministic payment policy guardrail for AI agents - budgets, allowlists, signed mandates.
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.