agentguard — policy proxy for agent tool calls

io.github.agentwares由 GitHub 账号 agentwares 发布v0.2.0更新于 Oct 27, 2026

Free spend report from an agent log, no key. Hosted proxies: caps, audit export, buy calls.

已验证Streamable HTTP可网页运行云端与基础设施安全与监控数据与分析

概览

AI 生成的概览

面向智能体工具调用的托管策略代理:可创建代理、设置上限与策略、查看运行、导出审计链并统计花费。

可以做什么
  • 在 MCP 服务器前创建并配置托管代理,返回代理地址与密钥
  • 替换代理策略,涵盖模式、上游、分类、上限、循环、试运行、审批、告警与漂移
  • 查看单次运行:调用计数、带决策的时间线、试运行变更、账本与审计链校验
  • 导出带哈希链的审计条目与 Merkle 根,用于争议处理与问卷答复
  • 根据智能体日志统计花费,包括总额、按工具调用、循环以及哪条上限本可阻止超支
  • 根据已记录调用推荐最小权限工具白名单,并读取机器可读的定价信息
适用场景
适合智能体调用大量工具、需要花费上限、循环检测、审批关卡与可审计记录的场景;也适合仅想从现有智能体日志免费得到花费报告的情况。
运行要求
远程 streamable HTTP 端点,无需本地安装。创建代理、修改策略、查看运行、导出审计与推荐白名单需要以 Authorization Bearer 头传入账户密钥;花费报告与定价工具无需密钥。账户可通过注册接口创建。
安装前请注意
账户密钥是敏感凭据,通过 Authorization 头传输。创建代理会返回仅显示一次的代理密钥,之后由它保护被代理的 MCP 服务器。策略可拦截、伪造或试运行工具调用,策略写错会改变智能体可做的事。购买调用次数会从预付余额扣款。审计导出包含已脱敏的参数。

安装

在 SourceWeft 中

  1. 打开 控制台中的 agentguard — policy proxy for agent tool calls,将其添加到工作区。
  2. 为需要使用其工具的对话启用该服务。

Web executable,通过 Streamable HTTP。 远程服务在工作区中配置后即可从网页运行时运行。

交给智能体安装

把这段提示词粘贴到 Claude Code、Codex、Cursor 等智能体,或 SourceWeft 对话中。智能体会读取该服务器的安装指南,先向你展示发布者、端点和登录方式,经你同意后再把它添加到你的客户端。密钥不会写进任何命令。

阅读 https://sourceweft.com/mcp/io.github.agentwares%2Fagentguard-cloud/install.md,并按其中说明把这个 MCP 服务器接入我的客户端。修改任何配置之前,先告诉我它的发布者、端点和登录方式,等我确认。不要把 API 密钥写进命令或我会提交的文件;问我密钥应从哪里获取。

查看智能体所依据的安装指南

其他 MCP 客户端

把它添加到你客户端的 mcpServers 配置中。

{
  "mcpServers": {
    "agentguard-policy-proxy-for-agent-tool-c": {
      "type": "http",
      "url": "https://agentwares-agentguard.vercel.app/api/mcp"
    }
  }
}

README

该仓库没有 README。

工具

7

okgate_get_pricing

Machine-readable pricing for okgate hosted: bands (Starter/Pro/Team) with included tool calls per month, the 80% soft alert and 150% hard stop, features, the free trial allowance, `per_call` — buying tool calls outright at POST /api/v1/calls from a prepaid balance, which is the one purchase here an unattended agent can complete — and `one_time`: reports a person pays for once on Stripe Checkout, such as the $49 EU AI Act Article 50 readiness report. Same data as /pricing.json.

无需输入参数。

okgate_spend_report

Read an agent log and report what it spent: totals, calls by tool and by class, estimated dollars by rail, loops, the largest single run, and — for every overspend — the okgate band whose cap would have stopped it, the exact cap, and the call that would have tripped it. Needs no account and no key. The log is read in the request and discarded; nothing is stored. Accepts an agentwares audit export (`agentwares.audit/v1`), a Claude Code session `.jsonl`, or a CSV/JSONL of tool calls with any of `tool`, `ts`, `class`, `amount_usd`, `rail`, `run_id`, `model`, `input_tokens`, `output_tokens`. Caps come from the proxy's own default policy, so a band named here refuses exactly what it says it refuses. Buying that band is a checkout a person completes; the calls-only purchase an unattended agent can complete is in `okgate_get_pricing` instead.

输入参数log必填detail

okgate_create_proxy

Create a hosted okgate proxy in front of an MCP server. Returns the proxy id, the per-customer MCP URL and the proxy key (shown once). Point your agent's MCP client at the URL with `Authorization: Bearer <key>`. Requires an account key.

输入参数modeslug必填upstreamUrl必填upstreamName

okgate_set_policy

Replace a proxy's policy (YAML: mode, upstreams, classify, caps, loop, dry_run, approvals, alerts, chaos, drift). Validated before saving; takes effect within 30 seconds. Requires an account key.

输入参数proxyId必填policyYaml必填

okgate_get_run

The incident-shaped report for one run: counts (calls, reads, writes, faked, blocked, spend), the call timeline with decisions, dry-run mutations (what would have changed), ledger entries and the audit-chain verification. Requires an account key.

输入参数runId必填proxyId必填

okgate_export_audit

Export a run's hash-chained audit entries (prev_hash, hash, redacted args) with the Merkle root, for disputes and questionnaires. Verify offline with sha256(prev_hash + canonical(entry)). Requires an account key.

输入参数runId必填proxyId必填

okgate_recommend_allowlist

Least-privilege recommendation from the proxy's recorded calls: the minimal tool allowlist, argument keys used per tool, and the upstream tools never used (remove them first). No LLM call here; apply it in the dashboard. Requires an account key.

输入参数proxyId必填

版本历史

1
  1. v0.2.0最新Sep 16, 2026

评分

已满足适用检查项的 75%

该评分衡量此收录条目的完整程度,依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价,也不表示服务器安全或当前可用:可连通性是带日期的检查结果,评分也不包含安装量或用户评价。

  • 近 30 天内可连通必需25 分
  • 已声明认证方式必需10 分
  • 已列出工具必需15 分
  • 描述必需15 分
  • 图标10 分
  • 文档15 分

    请声明包含 README 的 GitHub 仓库,或在 OAuth 受保护资源元数据中提供 resource_documentation。

  • 许可证10 分

    请在仓库或注册中心条目中声明许可证。