AI Skill Hub 推荐使用:MCP工具:Governance代理 是一款优质的MCP工具。AI 综合评分 7.5 分,在同类工具中表现稳健。如果你正在寻找可靠的MCP工具解决方案,这是一个值得深入了解的选择。
Governance代理,用于执行政策,路由批准,检查证据等功能,强化MCP的安全性和可靠性
MCP工具:Governance代理 是一款遵循 MCP(Model Context Protocol)标准协议的 AI 工具扩展。通过 MCP 协议,它可以让 Claude、Cursor 等主流 AI 客户端直接访问和操作外部工具、数据源和服务,实现 AI 能力的无缝扩展。无论是文件操作、数据库查询还是 API 调用,都可以通过自然语言在 AI 对话中直接触发,极大提升生产效率。
Governance代理,用于执行政策,路由批准,检查证据等功能,强化MCP的安全性和可靠性
MCP工具:Governance代理 是一款遵循 MCP(Model Context Protocol)标准协议的 AI 工具扩展。通过 MCP 协议,它可以让 Claude、Cursor 等主流 AI 客户端直接访问和操作外部工具、数据源和服务,实现 AI 能力的无缝扩展。无论是文件操作、数据库查询还是 API 调用,都可以通过自然语言在 AI 对话中直接触发,极大提升生产效率。
# 方式一:通过 Claude Code CLI 一键安装
claude skill install https://github.com/gethelio/helio
# 方式二:手动配置 claude_desktop_config.json
{
"mcpServers": {
"mcp---governance--": {
"command": "npx",
"args": ["-y", "helio"]
}
}
}
# 配置文件位置
# macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
# Windows: %APPDATA%/Claude/claude_desktop_config.json
# 安装后在 Claude 对话中直接使用 # 示例: 用户: 请帮我用 MCP工具:Governance代理 执行以下任务... Claude: [自动调用 MCP工具:Governance代理 MCP 工具处理请求] # 查看可用工具列表 # 在 Claude 中输入:"列出所有可用的 MCP 工具"
// claude_desktop_config.json 配置示例
{
"mcpServers": {
"mcp___governance__": {
"command": "npx",
"args": ["-y", "helio"],
"env": {
// "API_KEY": "your-api-key-here"
}
}
}
}
// 保存后重启 Claude Desktop 生效
<p align="center"> <h1 align="center">Helio</h1> <p align="center">Open-source governance proxy for AI agents</p> </p>
<p align="center"> <a href="https://github.com/gethelio/helio/actions/workflows/ci.yml"><img src="https://github.com/gethelio/helio/actions/workflows/ci.yml/badge.svg" alt="CI" /></a> <a href="https://github.com/gethelio/helio/blob/main/LICENSE"><img src="https://img.shields.io/badge/license-Apache%202.0-blue.svg" alt="License" /></a> <a href="https://www.npmjs.com/package/@gethelio/proxy"><img src="https://img.shields.io/npm/v/@gethelio/proxy.svg" alt="npm version" /></a> </p>
<p align="center"> <a href="./docs/getting-started.md">Getting Started</a> · <a href="./docs/configuration.md">Docs</a> · <a href="./CONTRIBUTING.md">Contributing</a> </p>
---
Helio is an MCP proxy that sits between your AI agents and the tools they use. Every tool call passes through Helio, which enforces policies, checks evidence, routes approvals, tracks spend, and records everything - without changing your agent code or your MCP servers.
npx @gethelio/proxy init
@gethelio/proxy is the only Node package you install. It ships the proxy runtime and bundled dashboard UI assets together.
Declare prerequisite actions in policy. The proxy tracks completed actions per session and blocks anything where prerequisites aren't met.
rules:
- match:
tool: 'process_refund'
requires: ['orders.lookup', 'customer.verify']
npx @gethelio/proxy init
This single package includes the built-in dashboard UI bundle.
Ready-made configurations for common patterns:
npx @gethelio/proxy init already created a helio.yaml in your project root. Open it and point upstream.url at your existing MCP server. Helio v0.1 proxies a single upstream MCP server. A fuller example with policies, audit, and a dashboard secret:
version: '1'
upstream:
url: 'http://localhost:8080/mcp' # Your existing MCP server
transport: streamable-http # streamable-http (default), sse, or stdio
listen:
port: 3000 # Helio listens here
policies:
default: allow
rules:
# Block destructive operations
- match:
tool: 'delete_*'
action: deny
feedback:
message: 'Destructive operations are disabled'
# Rate limit expensive API calls
- match:
tool: 'search_*'
action: rate_limit
limits:
max_calls: 100
window: 1h
key: tool
# Spend limit on payment tools
- match:
tool: 'create_payment'
action: spend_limit
limits:
max_spend:
field: '$.amount'
limit: 5000
currency: 'GBP'
window: 24h
audit:
storage: sqlite
retention: 90d
include_responses: true
dashboard:
enabled: true
port: 3100
api_secret: '${HELIO_DASHBOARD_SECRET}'
If your upstream requires a static credential (for example Authorization: Bearer … on a hosted MCP server), set upstream.headers — values support ${VAR} interpolation so secrets stay out of the file.
About dashboard.api_secret:
npx @gethelio/proxy init, your helio.yaml already contains a generated api_secret (a literal 32-byte hex value, also printed when you ran init). It's set — skip this step.helio.yaml by hand using the ${HELIO_DASHBOARD_SECRET} placeholder shown above, set the variable before start: export HELIO_DASHBOARD_SECRET="$(openssl rand -hex 32)"
from helio import HelioContext
Route sensitive actions to Slack, webhook, or the Helio dashboard. Configurable timeout and escalation, plus a dashboard-only break-glass override (REST API and dashboard UI; not exposed as a Slack button).
| Helio | Obot | Cerbos | Built-in (Anthropic / OpenAI) | Framework (LangChain / CrewAI) | |
|---|---|---|---|---|---|
| **What it governs** | Per-call actions with cross-call state | Which tools/MCPs are reachable | App-level authorization decisions | Agent permissions inside one platform | Agent behavior inside one framework |
| **Architecture** | Out-of-process MCP proxy | Out-of-process MCP gateway | Sidecar / library | In-platform | In-framework |
| **Open source** | ✅ Apache 2.0 | ✅ Apache 2.0 | ✅ Apache 2.0 | ❌ | Varies |
| **Time to value** | 5 minutes | Setup-dependent | Hours | Built-in | Built-in |
| **No agent code changes** | ✅ | ✅ | ❌ | ✅ (within platform) | ❌ |
| **Governs agents you didn't build** | ✅ Any MCP agent | ✅ Any MCP agent | ✅ (any app) | ❌ One platform only | ❌ One framework only |
| **Evidence grounding** | ✅ Cumulative across calls | ❌ | ❌ | ❌ | Limited |
| **Self-repair feedback** | ✅ Structured retry hints | ❌ | ❌ | ❌ | Limited |
| **Stateful spend / rate limits** | ✅ Per-tool, per-session¹ | Basic | ❌ | ❌ | Limited |
| **Approval workflows** | ✅ Slack, webhook, dashboard | ✅ | ❌ | Limited | Limited |
| **Audit trail (incl. downstream responses)** | ✅ Captures upstream MCP responses | Decision logs | Decision logs | Platform telemetry | Framework logs |
\* Per-tool and per-session spend limits ship in v0.1. Cross-tool spend aggregation is planned for v0.2.
该项目是一个开源的MCP工具,用于执行政策,路由批准,检查证据等功能,强化MCP的安全性和可靠性。代码质量良好,但缺乏活跃的社区和文档支持
AI Skill Hub 为第三方内容聚合平台,本页面信息基于公开数据整理,不对工具功能和质量作任何法律背书。
建议在沙箱或测试环境中充分验证后,再部署至生产环境,并做好必要的安全评估。
✅ Apache 2.0 — 宽松开源协议,可商用,需保留版权声明和 NOTICE 文件,含专利授权条款。
总体来看,MCP工具:Governance代理 是一款质量良好的MCP工具,在同类工具中具备一定竞争力。AI Skill Hub 将持续追踪其更新动态,建议收藏备用,结合自身场景选择合适时机引入使用。
| 原始名称 | helio |
| 原始描述 | 开源MCP工具:Governance proxy for MCP - enforce policies, route approvals, check evidence, tr。⭐5 · TypeScript |
| Topics | ai-agentmcpmcp-governancemcp-proxymodel-context-protocoltypescript |
| GitHub | https://github.com/gethelio/helio |
| License | Apache-2.0 |
| 语言 | TypeScript |
收录时间:2026-06-10 · 更新时间:2026-06-11 · License:Apache-2.0 · AI Skill Hub 不对第三方内容的准确性作法律背书。
选择 Agent 类型,复制安装指令后粘贴到对应客户端