经 AI Skill Hub 精选评估,MCP工具 获评「推荐使用」。已获得 2.5k 颗 GitHub Star,这款MCP工具在功能完整性、社区活跃度和易用性方面表现出色,AI 评分 7.5 分,适合有一定技术背景的用户使用。
基于能力的代理运行时,具有细粒度的策略,代理访问目录。开源的MCP工具,提供安全和灵活的代理管理。
MCP工具 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。
基于能力的代理运行时,具有细粒度的策略,代理访问目录。开源的MCP工具,提供安全和灵活的代理管理。
MCP工具 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/always-further/nono
# 方式二:手动配置 claude_desktop_config.json
{
"mcpServers": {
"mcp--": {
"command": "npx",
"args": ["-y", "nono"]
}
}
}
# 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 执行以下任务... Claude: [自动调用 MCP工具 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__": {
"command": "npx",
"args": ["-y", "nono"],
"env": {
// "API_KEY": "your-api-key-here"
}
}
}
}
// 保存后重启 Claude Desktop 生效
<img src="assets/logo.gif" alt="nono logo" width="600"/>
<p> From the creator of <a href="https://sigstore.dev"><strong>Sigstore</strong></a> <br/> <sub>The standard for secure software attestation, used by PyPI, npm, brew, and Maven Central</sub> </p> <p> <a href="https://opensource.org/licenses/Apache-2.0"><img src="https://img.shields.io/badge/License-Apache%202.0-blue.svg" alt="License"/></a> <a href="https://github.com/always-further/nono/actions/workflows/ci.yml"><img src="https://github.com/always-further/nono/actions/workflows/ci.yml/badge.svg" alt="CI Status"/></a> <a href="https://docs.nono.sh"><img src="https://img.shields.io/badge/Docs-docs.nono.sh-green.svg" alt="Documentation"/></a> </p> <p> <a href="https://discord.gg/pPcjYzGvbS"> <img src="https://img.shields.io/badge/Chat-Join%20Discord-7289da?style=for-the-badge&logo=discord&logoColor=white" alt="Join Discord"/> </a> <a href="https://alwaysfurther.ai/careers"> <img src="https://img.shields.io/badge/We're_Hiring-Join_the_team-ff4f00?style=for-the-badge&logo=githubsponsors&logoColor=white" alt="We're hiring"/> </a> <a href="https://github.com/marketplace/actions/agent-sign"> <img src="https://img.shields.io/badge/Secure_Action-agent--sign-2088FF?style=for-the-badge&logo=github-actions&logoColor=white" alt="agent-sign GitHub Action"/> </a> </p>
--- </div>
[!NOTE] In the lead-up to a 1.0 release, APIs are stabilizing. API changes may still occur where necessary, but will be kept to a minimum.
nono is a capability-based, policy-governed runtime for AI agents.
It gives a process narrowly scoped access to the host resources it actually needs: specific paths, network destinations, sockets, environment variables, credentials, and operations. Policies are explicit, composable, auditable, and enforced by kernel primitives.
nono fits the space between "run the agent directly on my machine with full access to keys and files" and "seal it inside a separate guest OS." Agents work inside real development environments, with host resources modeled as explicit capabilities.
A profile states what the agent may touch, and nono applies it. The core library is policy-free: it applies only the capabilities a caller provides. The CLI, profiles, and registry packages carry the policy - and all inbuilt policy can be extended or overridden, since policy is fully composable.
For organizations, that means policy can be reviewed, versioned, distributed, and reused. A team can ship a standard profile for a class of agents, collect supervised audit records, preserve rollback evidence, and keep sensitive credentials in a trusted proxy path instead of injecting them directly into the agent process.
---
| Feature | Description |
|---|---|
| **Kernel sandbox** | Landlock (Linux) + Seatbelt (macOS). Irreversible, inherited by child processes. |
| **Credential injection** | Proxy mode keeps API keys outside the sandbox entirely. Supports keystore, 1Password, Apple Passwords. |
| **Attestation** | Sigstore-based signing and verification of instruction files (SKILLS.md, CLAUDE.md, etc.). |
| **Network filtering** | Allowlist-based host and endpoint filtering via local proxy. Cloud metadata endpoints hard-denied. |
| **Snapshots** | Content-addressable rollback with SHA-256 dedup and Merkle tree integrity. |
| **Policy profiles** | Pre-built profiles for popular agents and use cases. Custom profile builder for your own needs. |
| **Audit logs** | Default event audit for supervised runs, optional append-only integrity hashing, and optional rollback-backed filesystem evidence. |
| **Cross-platform** | Support for macOS, Linux, and WSL2. Native Windows support in planning. |
| **Multiplexing** | Run multiple agents in parallel with separate sandboxes. Attach/detach to long-running agents. |
| **Runs anywhere** | Local CLI, CI pipelines, Containers / Kubernetes, cloud VMs, microVMs. |
See the full documentation for details and configuration.
Platform support: macOS, Linux, and WSL2.
Install:
brew install nono
Other options in the Installation Guide.
---
nono pull agent packages from the registry for all popular agents — Claude Code, Codex, Pi, Hermes, OpenCode, OpenClaw, and more — or build your own and securely share plugins, SKILLS, and hooks with the community or your team.
nono run --profile always-further/claude-code -- claude
MCP工具提供了安全和灵活的代理管理,适合安全和AI领域的使用,但需要进一步的测试和评估
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。
AI Skill Hub 点评:MCP工具 的核心功能完整,质量良好。对于Claude Desktop / Claude Code 用户来说,这是一个值得纳入个人工具库的选择。建议先在非生产环境试用,再逐步推广。
| 原始名称 | nono |
| 原始描述 | 开源MCP工具:Capability-based agent runtime with fine-grained policies . Brokering access dir。⭐2.5k · Rust |
| Topics | mcpagent-sandboxagent-securityai-agent-sandboxai-agent-securityai-agentsrust |
| GitHub | https://github.com/always-further/nono |
| License | Apache-2.0 |
| 语言 | Rust |
收录时间:2026-05-25 · 更新时间:2026-05-25 · 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