Command Palette

Search for a command to run...

UnylyUnyly
Весь каталог

Agent Commerce Guard

БесплатноНе проверен

Provides a read-only approval gate for AI agent commerce actions, reviewing up to five non-sensitive actions and returning decisions and required evidence witho

fxjimавтор: fxjim
GitHubEmbed

Описание

Provides a read-only approval gate for AI agent commerce actions, reviewing up to five non-sensitive actions and returning decisions and required evidence without executing, paying, or signing.

README

Approval gates and receipts for AI agents that can spend money, sell services, post socially, launch tokens, deploy publicly, or touch wallets.

Agent Commerce Guard is a local-first CLI and skill pack for builders adding x402, ACP, wallets, seller runtimes, paid APIs, or social integrations to autonomous agents.

Agent Commerce Guard preview

GitHub Action smoke Agent Skills installs

Try the free evaluator | Preview the paid package | Add the GitHub Action | Buy the private package for 1 USDC | Get support

The live evaluator includes one-click presets for wallet spend, production deploys, token launches, and marketplace jobs, so each decision path can be tested without writing a manifest first.

Free hosted preflight Private local package
Best for Public CI action manifests Private or sensitive agent workflows
Execution Hosted evaluator, up to 5 actions / 20 KB Local CLI, HTTP evaluator, skills, policies, and templates
Price Free 1 USDC on Base

The checkout links to the full sample report, Base MCP purchase recipe, and support before payment, then verifies the Base USDC transaction server-side. Both the checkout and success handoff retry pending receipts automatically before the private package unlocks. A submitted transaction hash is preserved in the current URL so a refresh resumes verification instead of losing the unlock path.

The public package proof shows the exact CLI report format and file inventory before payment. Canonical tests compare the samples to the current policy engine and verify each advertised file against the paid tarball:

Install The Free Evaluator Skill

Install a non-executing preflight workflow for public, non-sensitive action manifests:

npx skills add https://github.com/fxjim/agent-commerce-guard --skill try-agent-commerce-guard

The skill enforces the hosted-data boundary, evaluates at most five actions and 20 KB through the free endpoint, and hands private workflows to the paid local package without initiating a payment.

GitHub Copilot Plugin

Install the policy-only review plugin directly from GitHub:

copilot plugin install fxjim/agent-commerce-guard:plugins/agent-commerce-guard

The plugin's skill uses /api/policy-review, returns only decisions and required evidence, and includes no checkout or payment links. Its immutable 1.0.0 source is tagged copilot-plugin-v1.0.0. The official Awesome Copilot review is ready for review after passing its automated quality gates.

Remote MCP Server

Connect an MCP client to the public, stateless Streamable HTTP endpoint:

https://agent-commerce-guard.vercel.app/api/mcp

Codex:

codex mcp add agent-commerce-guard --url https://agent-commerce-guard.vercel.app/api/mcp

Claude Code:

claude mcp add --transport http agent-commerce-guard https://agent-commerce-guard.vercel.app/api/mcp

VS Code mcp.json:

{
  "servers": {
    "agent-commerce-guard": {
      "type": "http",
      "url": "https://agent-commerce-guard.vercel.app/api/mcp"
    }
  }
}

Setup and verification: Vercel guide or GitHub Pages mirror.

The server exposes one read-only, non-destructive tool, review_agent_commerce_actions. It accepts up to five non-sensitive public actions and 20 KB, returns decisions and required evidence, and does not execute, pay, sign, deploy, post, or include purchase instructions in tool output. MCP 1.2.0 also exposes one public JSON resource, https://agent-commerce-guard.vercel.app/offer.json, so clients can discover the exact 1 USDC Base offer without mixing purchase data into policy-tool results. Server initialization points clients to that resource, requires explicit approval before payment, and requires Base transaction verification after payment. The review-before-purchase prompt joins policy review, offer inspection, explicit approval, and receipt verification without initiating a payment. Registry metadata is available in server.json. The official Registry lists io.github.fxjim/agent-commerce-guard as an active remote server.

Install The Buyer Skill

Install the free public buyer workflow for Codex, Claude Code, Cursor, and other Agent Skills-compatible assistants:

npx skills add https://github.com/fxjim/agent-commerce-guard --skill buy-agent-commerce-guard

The same skill is also available from the canonical product domain:

npx skills add https://agent-commerce-guard.vercel.app --skill buy-agent-commerce-guard

The skill preflights the public offer and requires explicit approval before any Base Account, Base MCP, x402, browser-wallet, or manual payment. Its source is available at skills/buy-agent-commerce-guard/SKILL.md. Its indexed directory page is available on skills.sh. The paid product package remains available only after a verified 1 USDC payment.

GitHub Action

Run the free hosted policy preflight in an ubuntu-latest workflow:

- uses: fxjim/agent-commerce-guard@v1
  with:
    manifest: agent-commerce-actions.json
    fail-on: deny

The manifest may be a single action, an action array, or an object with an actions array. The Action sends at most five actions and 20 KB to the public hosted evaluator, prints sanitized decisions, and can fail on denied actions or actions requiring review. It rejects obvious secret-bearing JSON keys before the request.

The Action exposes checkout-url for the private local package, x402-evaluate-url for the paid workflow API, sample-report-url for the full CLI example, package-metadata-url for the machine-readable inventory, and base-mcp-recipe-url for an authorized Base MCP assistant. The job summary links to the proof and purchase paths after every completed evaluation.

Do not submit secrets, private source, credentials, or sensitive customer data. Use the paid local package when an action manifest cannot leave the runner. See examples/github-actions/ for a complete workflow and harmless example manifest.

Launch Pass

The launch pass is available for 1 USDC on Base.

What It Includes

  • CLI policy engine.
  • Agent skill pack for Codex, Claude, and OpenClaw-style workflows.
  • Approval log and launch checklist templates.
  • Action manifest examples.
  • Local HTTP evaluator.
  • Vercel-gated download flow.
  • Hosted demo endpoint that returns sanitized decisions without echoing submitted action text.
  • One-click hosted demo presets for wallet spend, production deploys, token launches, and marketplace jobs.
  • Free evaluator skill for non-sensitive action manifests with an explicit local-package handoff.
  • Free GitHub Action for CI policy preflight with local secret-key rejection and configurable failure behavior.
  • Demo responses include paid purchase metadata and exact x402 next-action commands.
  • Agent/plugin manifests for coding-agent, OpenAPI, x402, and LLM discovery.
  • Copy-paste purchase guides for x402 agents and manual Base buyers.
  • Machine-readable Base USDC payment request with an EIP-681 transfer URI.
  • Machine-readable payment metadata advertises both /verify?tx={tx} and /success?tx={tx} as post-payment unlock pages.
  • Product-specific Base MCP purchase recipe with exact chain, token, receiver, amount, and explicit approval constraints.
  • Free installable buyer skill with preflight, approval, verification, and unlock steps.
  • Scan-to-pay SVG QR for mobile wallet payment.
  • Homepage buyer-command section with exact x402 inspect/pay commands and copy buttons.
  • Social preview image wired into OG/Twitter/schema metadata.
  • Structured Product/SoftwareApplication metadata on the live homepage for search and crawler discovery.
  • IndexNow key route and refreshed submitted URL batch for faster search discovery.
  • Pinned GitHub launch/support issue for buyer questions and x402 integration notes.
  • Public GitHub launch discussion for product context and buyer discovery.
  • GitHub Pages launch page for search and buyer discovery.
  • Public GitHub Gist buyer brief with exact Base/x402 purchase commands.
  • GitHub Pages agent-readable mirrors for llms.txt, agents.json, agent.json, offer.json, .well-known/agent-commerce-guard.json, .well-known/offer.json, openapi.json, .well-known/openapi.json, .well-known/ai-plugin.json, package-metadata.json, .well-known/package-metadata.json, status.json, .well-known/status.json, .well-known/x402, .well-known/agents.json, .well-known/agent.json, .well-known/purchase.json, pay/, robots.txt, and sitemap.xml.
  • OpenAPI 3.1 spec for paid and demo endpoints.
  • x402 paid package endpoint for agent-native purchase on Base mainnet.
  • x402 paid evaluation endpoint for agent-native policy decisions over POSTed action manifests.
  • Discovery metadata for agent workflow validation, command-risk scoring, destructive-action review, and wallet-spend approval.
  • x402 Bazaar metadata tags: agent-commerce, agent-safety, guardrails, approval-gates, codex, x402.

Why It Exists

Agent commerce is moving faster than agent governance. This tool blocks or escalates actions that cross financial, production, social, token, or credential boundaries until there is explicit evidence and approval.

Agent Buyer Flow

  1. Read https://agent-commerce-guard.vercel.app/offer.json.
  2. Open https://agent-commerce-guard.vercel.app/pay and use the official Base Account control to review and confirm 1 USDC on Base mainnet.
  3. Or load https://agent-commerce-guard.vercel.app/base-mcp.json in an authorized Base MCP assistant, read https://agent-commerce-guard.vercel.app/pay.json for the exact manual Base payment request, or scan https://agent-commerce-guard.vercel.app/qr.
  4. Verify the transaction at /verify?tx={tx}, /success?tx={tx}, or /api/base-payment-status?tx={tx}. Both browser pages automatically retry a pending Base receipt and resume from the URL after a refresh.
  5. Download the package from /success?tx={tx} or /api/base-download?tx={tx}.

Agent buyers can also call https://agent-commerce-guard.vercel.app/api/x402-download directly and satisfy the returned x402 payment requirement.

Agent workflows can call POST https://agent-commerce-guard.vercel.app/api/x402-evaluate and satisfy the returned x402 payment requirement to receive a sanitized policy decision.

The x402 endpoints return Base-mainnet exact payment requirements for 1000000 atomic USDC and include route-level Bazaar metadata for agent discovery.

Purchase questions, wallet-flow issues, and x402 integration notes can go in the pinned launch/support issue: https://github.com/fxjim/agent-commerce-guard/issues/1.

Launch context and buyer discovery thread: https://github.com/fxjim/agent-commerce-guard/discussions/2.

from github.com/fxjim/agent-commerce-guard

Установка Agent Commerce Guard

У этого сервера нет опубликованного пакета — он собирается из исходников. Открой репозиторий и следуй инструкции в README.

▸ github.com/fxjim/agent-commerce-guard

FAQ

Agent Commerce Guard MCP бесплатный?

Да, Agent Commerce Guard MCP бесплатный — установка в пару кликов через Unyly без оплаты.

Нужен ли API-ключ для Agent Commerce Guard?

Нет, Agent Commerce Guard работает без API-ключей и переменных окружения.

Agent Commerce Guard — hosted или self-hosted?

Доступен hosted-вариант: Unyly запускает сервер в облаке, локальная установка не обязательна.

Как установить Agent Commerce Guard в Claude Desktop, Claude Code или Cursor?

Открой Agent Commerce Guard на unyly.org, выбери вкладку своего клиента (Claude Desktop, Claude Code, Cursor) и нажми Install — конфиг сгенерируется автоматически, без правки JSON.

Похожие MCP

Fetch

Web content fetching and conversion for efficient LLM usage.

автор: Community

AWS KB Retrieval

Retrieval from AWS Knowledge Base using Bedrock Agent Runtime.

modelcontextprotocolавтор: modelcontextprotocol

Spring AI MCP Server

Provides auto-configuration for setting up an MCP server in Spring Boot applications.

автор: Community

llm-analysis-assistant

A very streamlined mcp client that supports calling and monitoring stdio/sse/streamableHttp, and can also view request responses through the /logs page. It also

xuzexin-hzавтор: xuzexin-hz

Compare Agent Commerce Guard with

Agent Commerce GuardvsFetchAgent Commerce GuardvsAWS KB RetrievalAgent Commerce GuardvsSpring AI MCP ServerAgent Commerce Guardvsllm-analysis-assistant

Не уверен что выбрать?

Найди свой стек за 60 секунд

Автор?

Embed-бейдж для README

Похожее

Все в категории ai